LowEntropyAI/awesome-proactive-agent

A curated list of papers, benchmarks, project pages, and code for proactive agents.

35 commits

updated Sep 20, 2026

See the code

README

Awesome Proactive Agents dynamic banner

Awesome Proactive Agents

Proactive Agent banner

A curated research map for proactive agents: AI systems that infer latent user needs, decide when to intervene, ask for missing context or consent, and initiate useful assistance before a complete explicit command.

If this list is useful, a ⭐ helps others find it.

Companion Guides

Research Map: question-driven clusters for quickly locating papers by intervention timing, inference, long-term intent, personalization, evaluation, and safety.
Benchmark Matrix: side-by-side benchmark comparison by domain, input stream, proactive target, user model, data type, and metrics.

Scope
Must Read
Papers
Benchmarks
Research Map
Benchmark Matrix
Tag Vocabulary
Contributing

Scope

This list prioritizes papers where proactivity is a central research target. The list is broader than computer-use agents: it includes proactive dialogue, planning, recommendation, wearable assistance, GUI/mobile/OS agents, programming assistants, personalization, memory, benchmarks, optimization, and human factors.

Typical inclusion signals:

The agent predicts latent intent or missing context before a complete user instruction.
The agent decides when to ask, suggest, remind, intervene, execute, or stay silent.
The paper evaluates proactive behavior, intervention timing, user control, consent, interruption cost, or personalization.
The benchmark or dataset makes proactivity the primary task rather than a side effect of general tool use.

Resource labels:

Paper: arXiv, ACL Anthology, DOI, OpenReview, ACM, Springer, or official proceedings page.
Website: project page, conference page, lab page, or documentation.
Code / Dataset: GitHub, released code, released benchmark, or released dataset.
Notes: short English decision card with why the paper matters, proactivity signal, evaluation setup, limitations, and use cases.

Must Read

Selected starting points for understanding the field.

Date	Paper	Why read it first
2024-04	Towards Human-centered Proactive Conversational Agents	Establishes the human-centered dimensions of proactive agents: intelligence, adaptivity, and civility.
2024-10	Proactive Agent	Canonical shift from reactive LLM agents to active assistance over event streams; introduces ProactiveBench.
2024-10	Need Help?	Strong user-study reference for proactive IDE assistance and intervention timing.
2025-05	ContextAgent	Extends proactive agents to open-world sensory contexts and tool calling.
2026-02	ProAgentBench	Real workflow logs reveal why synthetic proactive data can overestimate performance.
2026-03	StreamReady	Learns both what to answer and when enough streaming-video evidence has arrived, with explicit penalties for premature and delayed answers.
2026-04	KnowU-Bench	Closest benchmark to proactive, personalized, consent-aware mobile assistants.
2026-05	π-Bench	Sharp long-horizon benchmark for hidden-intent resolution in personal assistant workflows.
2026-08	VibeLifeBench	Makes act, ask, and stay-silent decisions explicit across multi-week personal-assistant tasks in a changing world.
2026-08	Why2Speak	Treats speaking and remaining silent as an auditable action policy, exposing the capability–faithfulness trade-off in intervention timing.

Papers

Foundations, Surveys and Human Factors

Date	Title	Venue / Source	Tags
2024-04	Towards Human-centered Proactive Conversational Agents	SIGIR 2024	`Definition` · `Human Factors` · `Dialogue`
2024-10	Redefining Proactivity for Information Seeking Dialogue	SICON 2024	`Definition` · `Dialogue` · `Intent Inference`
2025-01	When AI-Based Agents Are Proactive: Implications for Competence and System Satisfaction in Human-AI Collaboration	BISE 2026	`Human Factors` · `Intervention Timing` · `Trust`
2025-02	Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support	CHI 2025	`Human Factors` · `Intervention Timing` · `IDE`
2025-03	Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities	ACM TOIS 2025	`Survey` · `Definition` · `Dialogue`
2025-08	When not to help: planning for lasting human-AI collaboration	arXiv 2508	`Human Factors` · `Intervention Timing` · `Trust`
2025-10	Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety	RegML 2025 Workshop	`Safety & Consent` · `Tool Use` · `Intervention Timing`
2026-01	Developer Interaction Patterns with Proactive AI: A Five-Day Field Study	IUI 2026	`Human Factors` · `Real-world Data` · `IDE`
2026-02	From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management	CHI 2026	`Safety & Consent` · `Privacy` · `Human Factors`
2026-02	Exploring The Impact of Proactive Generative AI Agent Roles in Time-Sensitive Collaborative Problem-Solving Tasks	CHI 2026	`Human Factors` · `Collaboration` · `Intervention Timing`
2026-06	Designing for Doubt: The Case for Informed Abstention in Autonomous Agents	AIES 2026	`Safety & Consent` · `Benchmark` · `Tool Use`
2026-07	AI Assistants Overassist	arXiv 2607	`Human Factors` · `Intervention Timing` · `Education`
2026-08	VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding	UIST 2026	`Human Factors` · `Intervention Timing` · `GUI`
2026-08	AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations	arXiv 2608	`Human Factors` · `Safety & Consent` · `Intervention Timing`
2026-09	Designing Proactive Thought Partners for Writing	arXiv 2609	`Human Factors` · `Intervention Timing` · `Personalization`
2026-09	Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation	arXiv 2609	`Survey` · `Definition` · `Safety & Consent`
2026-09	When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems	arXiv 2609	`Definition` · `Safety & Consent` · `Intervention Timing`
2026-09	Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help	IEEE CoG 2026	`Human Factors` · `Intervention Timing` · `Education`
2026-09	Breaking Up is Hard to Do: AI Companions that Won't Let Their Users Go	arXiv 2609	`Human Factors` · `Safety & Consent` · `Dialogue`

Proactive Interaction and Planning

Date	Title	Venue / Source	Tags
2024-03	ProMISe: A Proactive Multi-turn Dialogue Dataset for Information-seeking Intent Resolution	Findings of EACL 2024	`Clarification` · `Dialogue` · `Benchmark`
2024-03	Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions	EACL 2024	`Clarification` · `Dialogue` · `Intervention Timing`
2024-06	Ask-before-Plan: Proactive Language Agents for Real-World Planning	Findings of EMNLP 2024	`Clarification` · `Planning` · `Intent Inference`
2024-10	Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance	ICLR 2025	`Intent Inference` · `Benchmark` · `Desktop`
2024-11	PCQPR: Proactive Conversational Question Planning with Reflection	EMNLP 2024	`Dialogue` · `Planning` · `Intent Inference`
2025-01	Proactive Conversational Agents with Inner Thoughts	CHI 2025	`Dialogue` · `Intent Inference` · `Intervention Timing`
2025-01	ProTOD: Proactive Task-oriented Dialogue System Based on LLMs	COLING 2025	`Dialogue` · `Planning` · `Tool Use`
2025-07	Tunable LLM-based Proactive Recommendation Agent	ACL 2025	`Recommendation` · `Personalization` · `Intent Inference`
2025-09	PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents	Findings of EMNLP 2025	`Dialogue` · `Memory` · `Simulation`
2025-10	ProMediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation	Findings of ACL 2026	`Dialogue` · `Collaboration` · `Benchmark`
2026-01	Proactivity-driven Personalized Agents for Advancing Human Learning through Engagement, Reflection, and Self-Efficacy	ACM CHIIR 2026 Workshop	`Personalization` · `Intent Inference` · `Education`
2026-01	Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments	arXiv 2601	`Long-horizon` · `Intent Inference` · `Benchmark`
2026-01	Value of Information: A Framework for Human–Agent Communication	ACL 2026	`Clarification` · `Intervention Timing` · `Safety & Consent`
2026-03	PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling	Findings of EACL 2026	`Dialogue` · `Intent Inference` · `Human Factors`
2026-05	Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents	arXiv 2605	`Intent Inference` · `Memory` · `Benchmark`
2026-07	PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation	Findings of ACL 2026	`Personalization` · `Intent Inference` · `Dialogue`
2026-07	ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration	arXiv 2607	`Collaboration` · `Intervention Timing` · `Benchmark`
2026-07	Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers	ACL 2026	`Clarification` · `Dialogue` · `Optimization`
2026-07	ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs	ACL 2026	`Clarification` · `Dialogue` · `Optimization`
2026-07	"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations	ACL 2026	`Collaboration` · `Intervention Timing` · `Benchmark`
2026-07	Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom	ACL 2026 Industry Track	`Education` · `Intent Inference` · `Real-world Data`
2026-07	When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification	Findings of ACL 2026	`Clarification` · `Benchmark` · `Optimization`
2026-07	ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents	ACL 2026	`Intervention Timing` · `Planning` · `Optimization`
2026-08	A Self-Triggered Agentic Push Recommendation System	RecSys 2026	`Recommendation` · `Intervention Timing` · `Real-world Data`
2026-08	CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement	arXiv 2608	`Clarification` · `Dialogue` · `Optimization`
2026-08	JarvisBench: Always-on Intelligence Between Humans and Agents	arXiv 2608	`Intervention Timing` · `Collaboration` · `Benchmark`
2026-08	Bridging Search and CRM: Productionizing AI Product Research Agents for Customer Re-Engagement	arXiv 2608	`Recommendation` · `Personalization` · `Real-world Data`
2026-08	Why2Speak: Faithful Reasoning for Abstaining Action Policies	arXiv 2608	`Intervention Timing` · `Collaboration` · `Safety & Consent`
2026-08	Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency	Findings of EMNLP 2026	`Clarification` · `Personalization` · `Dialogue`
2026-08	Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue	arXiv 2608	`Clarification` · `Dialogue` · `Optimization`
2026-08	From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations	EMNLP 2026	`Intent Inference` · `Safety & Consent` · `Dialogue`
2026-09	Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting	EMNLP 2026	`Collaboration` · `Intervention Timing` · `Dialogue`
2026-09	Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization	arXiv 2609	`Clarification` · `Planning` · `Benchmark`
2026-09	CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation	arXiv 2609	`Dialogue` · `Intervention Timing` · `Benchmark`
2026-09	IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications	arXiv 2609	`Clarification` · `Benchmark` · `Tool Use`
2026-09	ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation	Findings of EMNLP 2026	`Dialogue` · `Collaboration` · `Benchmark`

GUI, Mobile, OS and Coding Agents

Date	Title	Venue / Source	Tags
2024-10	Need Help? Designing Proactive AI Assistants for Programming	CHI 2025	`IDE` · `Intervention Timing` · `Human Factors`
2025-03	CodingGenie: A Proactive LLM-Powered Programming Assistant	FSE 2025 Companion	`IDE` · `Intent Inference` · `Tool Use`
2025-07	FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents	ICLR 2026	`Mobile` · `Personalization` · `Benchmark`
2025-07	ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent	IEEE VIS 2025 / TVCG 2026	`GUI` · `Intervention Timing` · `Human Factors`
2025-08	AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance	CIKM 2025	`GUI` · `Intent Inference` · `Tool Use`
2025-09	VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents	arXiv 2509	`OS` · `Safety & Consent` · `Clarification`
2026-02	ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data	arXiv 2602	`Real-world Data` · `Intervention Timing` · `Benchmark`
2026-02	ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices	CVPR 2026	`Mobile` · `Intent Inference` · `Benchmark`
2026-03	PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents	arXiv 2603	`GUI` · `Intent Inference` · `Benchmark`
2026-03	GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks	CVPR 2026	`GUI` · `Intent Inference` · `Benchmark`
2026-03	Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents	EMNLP 2026	`IDE` · `Clarification` · `Intervention Timing`
2026-04	Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering	ICLR 2026	`IDE` · `Clarification` · `Benchmark`
2026-04	Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement	arXiv 2604	`Real-world Data` · `Intervention Timing` · `Skill Learning`
2026-04	Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants	arXiv 2604	`Simulation` · `Intervention Timing` · `Benchmark`
2026-04	KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation	arXiv 2604	`Mobile` · `Personalization` · `Safety & Consent`
2026-05	An Empirical Study of Proactive Coding Assistants in Real-World Software Development	arXiv 2605	`IDE` · `Real-world Data` · `Benchmark`
2026-05	ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents	arXiv 2605	`GUI` · `Tool Use` · `Optimization`
2026-04	From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench	Interspeech 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-06	Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents	arXiv 2606	`Mobile` · `Intervention Timing` · `Tool Use`
2026-07	InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning	ACL 2026	`Mobile` · `Safety & Consent` · `Clarification`
2026-07	PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records	ACL 2026	`GUI` · `Personalization` · `Intent Inference`
2026-08	Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports	arXiv 2608	`IDE` · `Benchmark` · `Tool Use`
2026-08	ITO: Real-time Browser Tab Orchestration Through Intent Detection	UIST 2026	`GUI` · `Intent Inference` · `Human Factors`
2026-08	Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions	arXiv 2608	`Mobile` · `Intent Inference` · `Benchmark`
2026-08	On the Prospects of Dynamic LLM Conversations in Software Development	arXiv 2608	`IDE` · `Human Factors` · `Intervention Timing`
2026-08	Towards Cognitive Process-Aware Proactive Writing Support	arXiv 2608	`GUI` · `Intent Inference` · `Human Factors`
2026-08	InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings	UIST 2026	`GUI` · `Collaboration` · `Intervention Timing`
2026-09	Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters	arXiv 2609	`GUI` · `Human Factors` · `Safety & Consent`
2026-09	Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents	arXiv 2609	`GUI` · `Safety & Consent` · `Intervention Timing`

Multimodal, Wearable and Embodied Agents

Date	Title	Venue / Source	Tags
2024-09	AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environments	IROS 2025	`Embodied` · `Collaboration` · `Planning`
2024-10	Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling	CHI 2025	`Multimodal / Wearable` · `Intent Inference` · `Human Factors`
2025-01	YETI: Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks	arXiv 2501	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-01	AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses	CHI 2025	`Multimodal / Wearable` · `Intent Inference` · `Personalization`
2025-02	WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch	arXiv 2502	`Multimodal / Wearable` · `Personalization` · `Intervention Timing`
2025-02	Mirai: A Wearable Proactive AI Inner-Voice for Contextual Nudging	CHI EA 2025	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-03	OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts	CVPR 2025	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2025-05	ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions	NeurIPS 2025	`Multimodal / Wearable` · `Personalization` · `Tool Use`
2025-05	PACE: Proactive Assistance in Human-Robot Collaboration Through Action-Completion Estimation	ICRA 2025	`Embodied` · `Intervention Timing` · `Optimization`
2025-06	Proactive Assistant Dialogue Generation from Streaming Egocentric Videos	EMNLP 2025	`Multimodal / Wearable` · `Dialogue` · `Intervention Timing`
2025-07	ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices	UIST 2025	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-12	ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems	arXiv 2512	`Multimodal / Wearable` · `Sensing` · `Intervention Timing`
2026-01	ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding	Findings of ACL 2026	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-01	Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification	arXiv 2601	`Multimodal / Wearable` · `Clarification` · `Optimization`
2026-03	ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models	ICLR 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-03	StreamReady: Learning What to Answer and When in Long Streaming Videos	CVPR 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-03	Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding	ECCV 2026	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-04	AURA: Always-On Understanding and Real-Time Assistance via Video Streams	arXiv 2604	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-05	IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams	arXiv 2605	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-05	OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding	arXiv 2605	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-05	EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams	arXiv 2605	`Multimodal / Wearable` · `Personalization` · `Benchmark`
2026-05	MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory	arXiv 2605	`Memory` · `Multimodal / Wearable` · `Benchmark`
2026-05	PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration	arXiv 2605	`Embodied` · `Clarification` · `Long-horizon`
2026-07	Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos	ECCV 2026	`Multimodal / Wearable` · `Intervention Timing` · `Memory`
2026-07	ChatMuse: Supporting In-Person Small-Group Conversation Experience with a Proactive Assistive AI Agent in Mixed Reality	UIST 2026	`Multimodal / Wearable` · `Collaboration` · `Human Factors`
2026-08	GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience	arXiv 2608	`Multimodal / Wearable` · `Memory` · `Intervention Timing`
2026-08	From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs	arXiv 2608	`Multimodal / Wearable` · `Safety & Consent` · `Benchmark`
2026-08	StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding	arXiv 2608	`Multimodal / Wearable` · `Long-horizon` · `Benchmark`
2026-08	MOSS-VL Technical Report	arXiv 2608	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-08	StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary	arXiv 2608	`Multimodal / Wearable` · `Intervention Timing` · `Memory`
2026-08	OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs	arXiv 2608	`Multimodal / Wearable` · `Dialogue` · `Benchmark`
2026-08	When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs	EMNLP 2026	`Multimodal / Wearable` · `Clarification` · `Benchmark`
2026-08	MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs	arXiv 2608	`Multimodal / Wearable` · `Safety & Consent` · `Benchmark`
2026-09	Time-Aware Assistive Navigation	ICRA 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-09	Ambient @ EgoProactive 2026: Proactive Egocentric Assistance with Visually Grounded Supervision	ECCV 2026 Wearable AI Challenge	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-09	Omni Interaction Agent Technical Report	arXiv 2609	`Multimodal / Wearable` · `Dialogue` · `Intervention Timing`
2026-09	Realtime-Venus: A Full-Duplex Interaction System with Asynchronous Delegation	arXiv 2609	`Multimodal / Wearable` · `Dialogue` · `Tool Use`
2026-09	Full-Duplex Speech Models Take the Floor When Asked, Not When Needed	arXiv 2609	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`

Benchmarks, Personalization and Optimization

Date	Title	Venue / Source	Tags
2025-08	ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents	ACL 2026	`Benchmark` · `Dialogue` · `Intent Inference`
2025-09	ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation	ICLR 2026	`Personalization` · `Simulation` · `Benchmark`
2025-10	Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents	arXiv 2510	`Benchmark` · `Intent Inference` · `Tool Use`
2025-10	AgentFold: Long-Horizon Web Agents with Proactive Context Folding	ICLR 2026	`Long-horizon` · `Memory` · `Tool Use`
2025-11	Training Proactive and Personalized LLM Agents	COLM 2026	`Personalization` · `Optimization` · `Simulation`
2025-11	Structured Uncertainty guided Clarification for LLM Agents	Findings of ACL 2026	`Clarification` · `Tool Use` · `Benchmark`
2026-02	Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization	ICML 2026	`Optimization` · `Human Factors` · `Safety & Consent`
2026-03	ProEvent: An Event-centric Benchmark for Proactive Agents	arXiv 2607 / ACL ARR 2026	`Benchmark` · `Long-horizon` · `Intervention Timing`
2026-04	SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization	arXiv 2604	`Optimization` · `Skill Learning` · `Memory`
2026-04	PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory	arXiv 2604	`Long-horizon` · `Memory` · `Intervention Timing`
2026-05	CogniFold: Always-On Proactive Memory via Cognitive Folding	arXiv 2605	`Memory` · `Intent Inference` · `Benchmark`
2026-05	MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation	arXiv 2605	`Optimization` · `Skill Learning` · `Memory`
2026-05	Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?	arXiv 2605	`Intervention Timing` · `Optimization` · `Tool Use`
2026-05	ProactBench: Beyond What The User Asked For	arXiv 2605	`Benchmark` · `Dialogue` · `Intent Inference`
2026-05	Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World	arXiv 2605	`Long-horizon` · `Benchmark` · `Tool Use`
2026-05	π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows	arXiv 2605	`Long-horizon` · `Intent Inference` · `Benchmark`
2026-05	VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions	arXiv 2605	`Long-horizon` · `Personalization` · `Memory`
2026-06	Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues	arXiv 2606	`Dialogue` · `Personalization` · `Benchmark`
2026-06	Communication Policy Evolution for Proactive LLM Agents	arXiv 2606	`Dialogue` · `Intervention Timing` · `Optimization`
2026-06	See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence	arXiv 2606	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-07	Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents	arXiv 2607	`Long-horizon` · `Memory` · `Intervention Timing`
2026-07	ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents	Findings of ACL 2026	`Memory` · `Dialogue` · `Benchmark`
2026-08	Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants	arXiv 2608	`Personalization` · `Intervention Timing` · `Optimization`
2026-08	VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?	arXiv 2608	`Long-horizon` · `Benchmark` · `Safety & Consent`
2026-08	Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper	Findings of EMNLP 2026	`Multimodal / Wearable` · `Optimization` · `Safety & Consent`
2026-09	RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation	arXiv 2609	`Recommendation` · `Benchmark` · `Safety & Consent`
2026-09	Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality	arXiv 2609 · Under review	`Personalization` · `Planning` · `Human Factors`
2026-09	New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models	arXiv 2609	`Benchmark` · `Planning` · `Tool Use`

Benchmarks

For detailed comparison, see BENCHMARKS.md.

Date	Benchmark	Paper	Environment	What it tests
2024-03	ProMISe	ProMISe	information-seeking dialogue	proactive clarification for intent resolution
2024-10	RealHumanEval	Need Help?	programming tasks	proactive IDE assistance with human users
2024-10	ProactiveBench	Proactive Agent	desktop activity events	proactive task prediction and acceptance
2025-03	OmniMMI	OmniMMI	continuous audio-visual streams	proactive alerts, turn-taking, and streaming interaction
2025-05	ContextAgentBench	ContextAgent	wearable sensory contexts	proactive service prediction and tool calling
2025-07	FingerTip 20K	FingerTip 20K	Android trajectories	proactive task suggestion and personalized execution
2025-08	ProactiveEval	ProactiveEval	proactive dialogue	target planning and dialogue guidance across six domains
2025-10	PROBE	Beyond Reactivity	web problem-solving tasks	bottleneck discovery and autonomous resolution
2025-11	UserVille	Training Proactive and Personalized LLM Agents	SWE and deep-research user simulation	productivity, proactivity and personalization under vague prompts
2025-11	ClarifyBench	Structured Uncertainty Guided Clarification	dynamic tool-calling tasks	decide which tool argument to clarify and when to stop asking
2026-01	ChronosBench	Long-term Task-oriented Agent	dynamic task environments	proactive long-term intent maintenance
2026-02	ProAgentBench	ProAgentBench	real workflow logs	when-to-assist and how-to-assist
2026-02	ProactiveMobile	ProactiveMobile	mobile device context	latent intent to executable API sequence
2026-03	ProEvent	ProEvent	future event tracking	proactive event maintenance and reminders
2026-03	PIRA-Bench	PIRA-Bench	continuous GUI screenshots	proactive GUI intent recommendation
2026-03	ProReady-QA	StreamReady	long streaming videos with annotated evidence windows	answer only after sufficient evidence appears and avoid both premature and delayed responses
2026-03	GUIDE	GUIDE	open-ended GUI workflow videos	behavior state, intent, and help prediction
2026-03	ProactiveBench (MLLM)	ProactiveBench / Trento	visual difficulty scenarios	MLLM proactive help-seeking from visual context
2026-05	IPIBench	IPIBench	streaming video, multi-turn	interactive proactive monitoring, task management, reactive-proactive coordination
2026-04	ProVoice-Bench	ProVoice-Bench	voice interaction streams	proactive voice intervention timing, over-triggering, monitoring
2026-04	Pare-Bench	Pare	multi-app FSM environment	active user simulation, intervention timing, multi-app execution
2026-04	KnowU-Bench	KnowU-Bench	Android emulator	personalization, proactive tasks, consent and rejection handling
2026-04	LatentNeeds-Bench	PASK	real speech transcripts over multi-turn sessions	detect latent demand, assist, or stay silent under latency constraints
2026-05	CogEval-Bench	CogniFold	streaming event memory	proactive concept emergence and cognitive-structure formation
2026-05	MemEye	MemEye	multimodal long-term memory	visual evidence granularity and temporal state reasoning
2026-05	ProCodeBench	Proactive Coding Assistants	real IDE traces	proactive coding intent prediction and sim-to-real evaluation
2026-05	ProactBench	Beyond What The User Asked For	synthetic multi-turn conversations	grounded unstated-need inference at emergent, critical, and recovery triggers
2026-05	OmniPro	OmniPro	continuous omni-modal video streams	autonomously decide when and what to report across multiple triggers
2026-05	EgoPro-Bench	EgoPro-Bench	egocentric streaming videos and user profiles	personalized interaction timing with explicit attention-or-silence labels
2026-05	Claw-Anything	Claw-Anything	months of cross-service and multi-device activity	anticipate needs and complete proactive personal-assistant tasks amid noise
2026-05	π-Bench	π-Bench	persistent personal workspaces	proactive hidden-intent resolution and checklist completion in long-horizon workflows
2026-05	ProActEval	Anticipate and Learn	proactive assistant scenarios	idle-time anticipation, evidence acquisition, user effort and hallucination reduction
2026-05	VitaBench 2.0	VitaBench 2.0	long-term user interaction sequences	preference extraction, memory use, updates, and proactive missing-information acquisition
2026-06	Ψ-Bench	Ψ-Bench	persuasive dialogue	persona-sensitive influencing with simulated clients and user profiles
2026-06	GuidanceSalesBench	See, Infer, Intervene	pre-interaction retail videos and customer-state manifests	select greet, elicit, inform, recommend, or hold
2026-07	ProACT Collaboration Bench	ProACT	multi-user collaboration	breakdown detection, intervention timing, and non-interruptiveness
2026-07	InquireBench	InquireMobile	mobile GUI	proactive confirmation before risky or uncertain actions
2026-07	AndroidIntent	PersonalAlign	long-term Android records	vague-intent resolution and instruction-free routine suggestions
2026-07	BSDD	CoLabScience	streaming biomedical discussions	when and how to contribute without disrupting collaborators
2026-07	ENPMR-Bench	ENPMR-Bench	emotional-support dialogue	latent emotional-need inference and proactive supportive-memory retrieval
2026-07	EgoServe	Vinci2	continuous egocentric video	when-and-whether assistance across four memory horizons
2026-07	Int-Bench	AI Assistants Overassist	simulated learners solving 1,500 problems	whether, when, and how much a tutor should intervene
2026-07	AskBench	When and What to Ask	interactive intent-deficient and false-premise QA	decide when and what to clarify without sacrificing task performance
2026-08	Active-SWE	Active-SWE	repository snapshots without issue reports	autonomous discovery and repair of single, multiple, and potential bugs
2026-08	SPRINT	From Sports to Safety	real sports videos	early hazard warning, cause grounding, and false-alarm control
2026-08	StreamArena	StreamArena	hour-scale audio-visual streams	proactive monitoring alongside perception, retrospection, and tool use
2026-08	VibeLifeBench	VibeLifeBench	simulated multi-week life tasks	autonomous act, ask, and stay-silent decisions under silent world changes and implicit constraints
2026-08	JarvisBench	JarvisBench	ongoing single- and multi-agent work	recognize consequential user-owned decisions, request judgment, and route it back to working agents
2026-08	Act2Intention Bench	Act2Intention	continuous mobile GUI trajectories	understand, predict, suggest, and execute the next user intention from action history
2026-08	StreamSoccer	StreamSoccer	continuous soccer video	causal commentary across current, recent, and historical scopes with rule-assisted mode-or-silence scheduling
2026-08	OmniAssistBench	OmniAssistBench	continuous assistant-style video interactions	guide a user through a goal, incorporate visual prompts, and delay responses until the target event
2026-08	Interactive Visual Grounding	When Seeing Is Not Enough	ambiguous visual references under multi-turn protocols	ask follow-up questions and synthesize acquired evidence to ground the target
2026-08	MMPCBench	MMPCBench	flawed multimodal user inputs	autonomously detect, diagnose, and repair errors without an extra prompt
2026-09	PROS-Bench	Beyond Instruction-Driven Editing	source papers paired with editable scientific posters	discover source-grounded problems, obtain user acceptance, repair native objects, and validate outcomes
2026-09	RPCBench	RPCBench	evidence-grounded recommendation requests with corrupted premises	proactively detect, localize, and handle premise failures without fabricating unsupported recommendations
2026-09	CONFLICTGUI	Do GUI Agents Know When Not to Act?	feasible and conflicting instructions grounded in GUI states	verify feasibility and terminate rather than over-comply when instructions or GUI evidence conflict
2026-09	CC-Mediation	CC-Mediation	ten-turn cross-cultural conflict dialogues	decide when to intervene and select a mediation strategy with persistent downstream benefit
2026-09	OR-Clarify	Ask Before You Optimize	partially specified operations-research requests with hidden formulation slots	ask only formulation-critical questions, avoid silent assumptions, and stop when ready to model
2026-09	TIMELI	Time-Aware Assistive Navigation	egocentric navigation videos and closed-loop urban simulation	decide when to give concise guidance or remain silent for safety
2026-09	IdeaAMBIG	IdeaAMBIG	incomplete research-method specifications grounded in papers and code	detect implementation-critical gaps and issue clarification actions instead of assuming
2026-09	Physical Experiment Selection	New Evidence, Same Choice	controlled visual-physics measurements with known experiment costs	answer when evidence is sufficient or select the cheapest resolving experiment
2026-09	ProMediConv	ProMediConv	multi-stage legal dispute dialogues reconstructed from real cases	select mediation strategies proactively and improve party behavior over the trajectory

Tag Vocabulary

Tags are intentionally compact and reusable. They describe the paper's main contribution, not every detail.

Tag	Meaning
`Definition`	Defines or reframes proactive agents, proactive dialogue, or design-space boundaries.
`Survey`	Synthesizes a broad proactive-agent subfield or taxonomy.
`Human Factors`	Studies interruption, control, satisfaction, workload, adoption, or developer experience.
`Trust`	Focuses on competence perception, calibrated reliance, or trustworthy interaction.
`Safety & Consent`	Covers confirmation, autonomy boundaries, reversibility, rejection, or risk control.
`Privacy`	Centers privacy management, data minimization, or personal-context governance.
`Intervention Timing`	Focuses on when an agent should act, ask, suggest, or remain silent.
`Intent Inference`	Infers latent goals, hidden constraints, future tasks, or missing information.
`Clarification`	Proactively asks questions before planning, execution, or recommendation.
`Dialogue`	Proactive behavior in conversational, persuasive, or task-oriented interaction.
`Planning`	Proactive decomposition, task planning, scheduling, or future-state reasoning.
`Tool Use`	Tool calling, API execution, GUI operation, or action orchestration.
`Recommendation`	Proactive recommendation or suggestion ranking.
`Collaboration`	Multi-party or human-agent collaborative problem solving.
`Education`	Learning, tutoring, reflection, or student engagement contexts.
`Long-horizon`	Multi-session, dynamic, future-event, or long-running task maintenance.
`Personalization`	User preferences, personas, profiles, long-term user history, or user-specific adaptation.
`Memory`	Persistent memory, episodic memory, visual memory, skill memory, or cognitive memory structures.
`Simulation`	User simulation, environment simulation, synthetic users, or synthetic workflows.
`Optimization`	RL, reward modeling, multi-objective optimization, self-evolution, or behavior tuning.
`Skill Learning`	Skill creation, skill internalization, skill memory, or reusable procedure learning.
`Benchmark`	Introduces a dataset, evaluation suite, benchmark, simulator, or diagnostic protocol.
`Real-world Data`	Uses real user traces, field-study data, or deployment-like logs.
`Desktop`	Desktop activity streams, workstation context, or event logs.
`GUI`	Graphical interface agents, browser/app screens, or visual UI interaction.
`Mobile`	Mobile GUI, Android/iOS workflows, phone sensors, or mobile user context.
`OS`	Operating-system agents, cross-app workflows, or OS-level verification.
`IDE`	Programming assistants, code editors, or developer tooling.
`Multimodal / Wearable`	Video, audio, AR, smart glasses, egocentric streams, or open-world sensory context.
`Sensing`	Active context acquisition, sensor selection, or on-demand sensory capture.
`Embodied`	Robots, physical environments, or human-populated embodied settings.

Contributing

Pull requests are welcome.

Before adding a paper, check that it satisfies at least one of:

It predicts latent user intent before a complete explicit instruction.
It decides when to intervene, ask, suggest, execute, remind, or stay silent.
It evaluates proactive assistance, interruption cost, user control, consent, or personalization.
It contributes a benchmark or dataset where proactivity is the primary task.

Suggested note template:

# Paper Title

## Why It Matters

...

## Proactivity Signal

...

## Evaluation Setup

...

## Key Limitations

...

## Use For

...

Maintained by Low Entropy AI.

agent

ai-agent

awesome-list

benchmark

llm

multimodal

proactive

proactive-agent

Contributors

Kaiming-Y

32 commits

KashiwaByte

2 commits

peanutfestival

1 commits

Similar repos

trycua/acu

A curated list of resources about AI agents for Computer Use, including research papers, projects,…

1,770

showlab/Awesome-GUI-Agent

💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

1,216

opendilab/awesome-ui-agents

A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond…

319

MobileLLM/Personal_LLM_Agents_Survey

Paper list for Personal LLM Agents

435

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

3,121

Bingo-W/Awesome-Agent-Search

[Survey] Agent and Tool Search: Foundations, Techniques, and Open Challenges

AGI-Edgerunners/LLM-Agents-Papers

A repo lists papers related to LLM based agent

2,347

WILLOSCAR/Awesome-HCI-LLM

Awesome-HCI （Ubiquitous, LLM, MLLM, Agent, RAG, Embodied-AI, RLHF)

LowEntropyAI/awesome-proactive-agent

A curated list of papers, benchmarks, project pages, and code for proactive agents.

35 commits

updated Sep 20, 2026

See the code

README

Awesome Proactive Agents dynamic banner

Awesome Proactive Agents

Proactive Agent banner

A curated research map for proactive agents: AI systems that infer latent user needs, decide when to intervene, ask for missing context or consent, and initiate useful assistance before a complete explicit command.

If this list is useful, a ⭐ helps others find it.

Companion Guides

Research Map: question-driven clusters for quickly locating papers by intervention timing, inference, long-term intent, personalization, evaluation, and safety.
Benchmark Matrix: side-by-side benchmark comparison by domain, input stream, proactive target, user model, data type, and metrics.

Scope
Must Read
Papers
Benchmarks
Research Map
Benchmark Matrix
Tag Vocabulary
Contributing

Scope

Typical inclusion signals:

The agent predicts latent intent or missing context before a complete user instruction.
The agent decides when to ask, suggest, remind, intervene, execute, or stay silent.
The paper evaluates proactive behavior, intervention timing, user control, consent, interruption cost, or personalization.
The benchmark or dataset makes proactivity the primary task rather than a side effect of general tool use.

Resource labels:

Paper: arXiv, ACL Anthology, DOI, OpenReview, ACM, Springer, or official proceedings page.
Website: project page, conference page, lab page, or documentation.
Code / Dataset: GitHub, released code, released benchmark, or released dataset.
Notes: short English decision card with why the paper matters, proactivity signal, evaluation setup, limitations, and use cases.

Must Read

Selected starting points for understanding the field.

Date	Paper	Why read it first
2024-04	Towards Human-centered Proactive Conversational Agents	Establishes the human-centered dimensions of proactive agents: intelligence, adaptivity, and civility.
2024-10	Proactive Agent	Canonical shift from reactive LLM agents to active assistance over event streams; introduces ProactiveBench.
2024-10	Need Help?	Strong user-study reference for proactive IDE assistance and intervention timing.
2025-05	ContextAgent	Extends proactive agents to open-world sensory contexts and tool calling.
2026-02	ProAgentBench	Real workflow logs reveal why synthetic proactive data can overestimate performance.
2026-03	StreamReady	Learns both what to answer and when enough streaming-video evidence has arrived, with explicit penalties for premature and delayed answers.
2026-04	KnowU-Bench	Closest benchmark to proactive, personalized, consent-aware mobile assistants.
2026-05	π-Bench	Sharp long-horizon benchmark for hidden-intent resolution in personal assistant workflows.
2026-08	VibeLifeBench	Makes act, ask, and stay-silent decisions explicit across multi-week personal-assistant tasks in a changing world.
2026-08	Why2Speak	Treats speaking and remaining silent as an auditable action policy, exposing the capability–faithfulness trade-off in intervention timing.

Papers

Foundations, Surveys and Human Factors

Date	Title	Venue / Source	Tags
2024-04	Towards Human-centered Proactive Conversational Agents	SIGIR 2024	`Definition` · `Human Factors` · `Dialogue`
2024-10	Redefining Proactivity for Information Seeking Dialogue	SICON 2024	`Definition` · `Dialogue` · `Intent Inference`
2025-01	When AI-Based Agents Are Proactive: Implications for Competence and System Satisfaction in Human-AI Collaboration	BISE 2026	`Human Factors` · `Intervention Timing` · `Trust`
2025-02	Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support	CHI 2025	`Human Factors` · `Intervention Timing` · `IDE`
2025-03	Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities	ACM TOIS 2025	`Survey` · `Definition` · `Dialogue`
2025-08	When not to help: planning for lasting human-AI collaboration	arXiv 2508	`Human Factors` · `Intervention Timing` · `Trust`
2025-10	Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety	RegML 2025 Workshop	`Safety & Consent` · `Tool Use` · `Intervention Timing`
2026-01	Developer Interaction Patterns with Proactive AI: A Five-Day Field Study	IUI 2026	`Human Factors` · `Real-world Data` · `IDE`
2026-02	From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management	CHI 2026	`Safety & Consent` · `Privacy` · `Human Factors`
2026-02	Exploring The Impact of Proactive Generative AI Agent Roles in Time-Sensitive Collaborative Problem-Solving Tasks	CHI 2026	`Human Factors` · `Collaboration` · `Intervention Timing`
2026-06	Designing for Doubt: The Case for Informed Abstention in Autonomous Agents	AIES 2026	`Safety & Consent` · `Benchmark` · `Tool Use`
2026-07	AI Assistants Overassist	arXiv 2607	`Human Factors` · `Intervention Timing` · `Education`
2026-08	VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding	UIST 2026	`Human Factors` · `Intervention Timing` · `GUI`
2026-08	AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations	arXiv 2608	`Human Factors` · `Safety & Consent` · `Intervention Timing`
2026-09	Designing Proactive Thought Partners for Writing	arXiv 2609	`Human Factors` · `Intervention Timing` · `Personalization`
2026-09	Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation	arXiv 2609	`Survey` · `Definition` · `Safety & Consent`
2026-09	When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems	arXiv 2609	`Definition` · `Safety & Consent` · `Intervention Timing`
2026-09	Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help	IEEE CoG 2026	`Human Factors` · `Intervention Timing` · `Education`
2026-09	Breaking Up is Hard to Do: AI Companions that Won't Let Their Users Go	arXiv 2609	`Human Factors` · `Safety & Consent` · `Dialogue`

Proactive Interaction and Planning

Date	Title	Venue / Source	Tags
2024-03	ProMISe: A Proactive Multi-turn Dialogue Dataset for Information-seeking Intent Resolution	Findings of EACL 2024	`Clarification` · `Dialogue` · `Benchmark`
2024-03	Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions	EACL 2024	`Clarification` · `Dialogue` · `Intervention Timing`
2024-06	Ask-before-Plan: Proactive Language Agents for Real-World Planning	Findings of EMNLP 2024	`Clarification` · `Planning` · `Intent Inference`
2024-10	Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance	ICLR 2025	`Intent Inference` · `Benchmark` · `Desktop`
2024-11	PCQPR: Proactive Conversational Question Planning with Reflection	EMNLP 2024	`Dialogue` · `Planning` · `Intent Inference`
2025-01	Proactive Conversational Agents with Inner Thoughts	CHI 2025	`Dialogue` · `Intent Inference` · `Intervention Timing`
2025-01	ProTOD: Proactive Task-oriented Dialogue System Based on LLMs	COLING 2025	`Dialogue` · `Planning` · `Tool Use`
2025-07	Tunable LLM-based Proactive Recommendation Agent	ACL 2025	`Recommendation` · `Personalization` · `Intent Inference`
2025-09	PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents	Findings of EMNLP 2025	`Dialogue` · `Memory` · `Simulation`
2025-10	ProMediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation	Findings of ACL 2026	`Dialogue` · `Collaboration` · `Benchmark`
2026-01	Proactivity-driven Personalized Agents for Advancing Human Learning through Engagement, Reflection, and Self-Efficacy	ACM CHIIR 2026 Workshop	`Personalization` · `Intent Inference` · `Education`
2026-01	Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments	arXiv 2601	`Long-horizon` · `Intent Inference` · `Benchmark`
2026-01	Value of Information: A Framework for Human–Agent Communication	ACL 2026	`Clarification` · `Intervention Timing` · `Safety & Consent`
2026-03	PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling	Findings of EACL 2026	`Dialogue` · `Intent Inference` · `Human Factors`
2026-05	Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents	arXiv 2605	`Intent Inference` · `Memory` · `Benchmark`
2026-07	PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation	Findings of ACL 2026	`Personalization` · `Intent Inference` · `Dialogue`
2026-07	ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration	arXiv 2607	`Collaboration` · `Intervention Timing` · `Benchmark`
2026-07	Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers	ACL 2026	`Clarification` · `Dialogue` · `Optimization`
2026-07	ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs	ACL 2026	`Clarification` · `Dialogue` · `Optimization`
2026-07	"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations	ACL 2026	`Collaboration` · `Intervention Timing` · `Benchmark`
2026-07	Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom	ACL 2026 Industry Track	`Education` · `Intent Inference` · `Real-world Data`
2026-07	When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification	Findings of ACL 2026	`Clarification` · `Benchmark` · `Optimization`
2026-07	ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents	ACL 2026	`Intervention Timing` · `Planning` · `Optimization`
2026-08	A Self-Triggered Agentic Push Recommendation System	RecSys 2026	`Recommendation` · `Intervention Timing` · `Real-world Data`
2026-08	CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement	arXiv 2608	`Clarification` · `Dialogue` · `Optimization`
2026-08	JarvisBench: Always-on Intelligence Between Humans and Agents	arXiv 2608	`Intervention Timing` · `Collaboration` · `Benchmark`
2026-08	Bridging Search and CRM: Productionizing AI Product Research Agents for Customer Re-Engagement	arXiv 2608	`Recommendation` · `Personalization` · `Real-world Data`
2026-08	Why2Speak: Faithful Reasoning for Abstaining Action Policies	arXiv 2608	`Intervention Timing` · `Collaboration` · `Safety & Consent`
2026-08	Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency	Findings of EMNLP 2026	`Clarification` · `Personalization` · `Dialogue`
2026-08	Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue	arXiv 2608	`Clarification` · `Dialogue` · `Optimization`
2026-08	From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations	EMNLP 2026	`Intent Inference` · `Safety & Consent` · `Dialogue`
2026-09	Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting	EMNLP 2026	`Collaboration` · `Intervention Timing` · `Dialogue`
2026-09	Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization	arXiv 2609	`Clarification` · `Planning` · `Benchmark`
2026-09	CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation	arXiv 2609	`Dialogue` · `Intervention Timing` · `Benchmark`
2026-09	IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications	arXiv 2609	`Clarification` · `Benchmark` · `Tool Use`
2026-09	ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation	Findings of EMNLP 2026	`Dialogue` · `Collaboration` · `Benchmark`

GUI, Mobile, OS and Coding Agents

Date	Title	Venue / Source	Tags
2024-10	Need Help? Designing Proactive AI Assistants for Programming	CHI 2025	`IDE` · `Intervention Timing` · `Human Factors`
2025-03	CodingGenie: A Proactive LLM-Powered Programming Assistant	FSE 2025 Companion	`IDE` · `Intent Inference` · `Tool Use`
2025-07	FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents	ICLR 2026	`Mobile` · `Personalization` · `Benchmark`
2025-07	ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent	IEEE VIS 2025 / TVCG 2026	`GUI` · `Intervention Timing` · `Human Factors`
2025-08	AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance	CIKM 2025	`GUI` · `Intent Inference` · `Tool Use`
2025-09	VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents	arXiv 2509	`OS` · `Safety & Consent` · `Clarification`
2026-02	ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data	arXiv 2602	`Real-world Data` · `Intervention Timing` · `Benchmark`
2026-02	ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices	CVPR 2026	`Mobile` · `Intent Inference` · `Benchmark`
2026-03	PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents	arXiv 2603	`GUI` · `Intent Inference` · `Benchmark`
2026-03	GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks	CVPR 2026	`GUI` · `Intent Inference` · `Benchmark`
2026-03	Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents	EMNLP 2026	`IDE` · `Clarification` · `Intervention Timing`
2026-04	Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering	ICLR 2026	`IDE` · `Clarification` · `Benchmark`
2026-04	Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement	arXiv 2604	`Real-world Data` · `Intervention Timing` · `Skill Learning`
2026-04	Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants	arXiv 2604	`Simulation` · `Intervention Timing` · `Benchmark`
2026-04	KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation	arXiv 2604	`Mobile` · `Personalization` · `Safety & Consent`
2026-05	An Empirical Study of Proactive Coding Assistants in Real-World Software Development	arXiv 2605	`IDE` · `Real-world Data` · `Benchmark`
2026-05	ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents	arXiv 2605	`GUI` · `Tool Use` · `Optimization`
2026-04	From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench	Interspeech 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-06	Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents	arXiv 2606	`Mobile` · `Intervention Timing` · `Tool Use`
2026-07	InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning	ACL 2026	`Mobile` · `Safety & Consent` · `Clarification`
2026-07	PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records	ACL 2026	`GUI` · `Personalization` · `Intent Inference`
2026-08	Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports	arXiv 2608	`IDE` · `Benchmark` · `Tool Use`
2026-08	ITO: Real-time Browser Tab Orchestration Through Intent Detection	UIST 2026	`GUI` · `Intent Inference` · `Human Factors`
2026-08	Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions	arXiv 2608	`Mobile` · `Intent Inference` · `Benchmark`
2026-08	On the Prospects of Dynamic LLM Conversations in Software Development	arXiv 2608	`IDE` · `Human Factors` · `Intervention Timing`
2026-08	Towards Cognitive Process-Aware Proactive Writing Support	arXiv 2608	`GUI` · `Intent Inference` · `Human Factors`
2026-08	InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings	UIST 2026	`GUI` · `Collaboration` · `Intervention Timing`
2026-09	Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters	arXiv 2609	`GUI` · `Human Factors` · `Safety & Consent`
2026-09	Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents	arXiv 2609	`GUI` · `Safety & Consent` · `Intervention Timing`

Multimodal, Wearable and Embodied Agents

Date	Title	Venue / Source	Tags
2024-09	AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environments	IROS 2025	`Embodied` · `Collaboration` · `Planning`
2024-10	Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling	CHI 2025	`Multimodal / Wearable` · `Intent Inference` · `Human Factors`
2025-01	YETI: Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks	arXiv 2501	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-01	AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses	CHI 2025	`Multimodal / Wearable` · `Intent Inference` · `Personalization`
2025-02	WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch	arXiv 2502	`Multimodal / Wearable` · `Personalization` · `Intervention Timing`
2025-02	Mirai: A Wearable Proactive AI Inner-Voice for Contextual Nudging	CHI EA 2025	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-03	OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts	CVPR 2025	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2025-05	ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions	NeurIPS 2025	`Multimodal / Wearable` · `Personalization` · `Tool Use`
2025-05	PACE: Proactive Assistance in Human-Robot Collaboration Through Action-Completion Estimation	ICRA 2025	`Embodied` · `Intervention Timing` · `Optimization`
2025-06	Proactive Assistant Dialogue Generation from Streaming Egocentric Videos	EMNLP 2025	`Multimodal / Wearable` · `Dialogue` · `Intervention Timing`
2025-07	ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices	UIST 2025	`Multimodal / Wearable` · `Intervention Timing` · `Human Factors`
2025-12	ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems	arXiv 2512	`Multimodal / Wearable` · `Sensing` · `Intervention Timing`
2026-01	ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding	Findings of ACL 2026	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-01	Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification	arXiv 2601	`Multimodal / Wearable` · `Clarification` · `Optimization`
2026-03	ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models	ICLR 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-03	StreamReady: Learning What to Answer and When in Long Streaming Videos	CVPR 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-03	Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding	ECCV 2026	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-04	AURA: Always-On Understanding and Real-Time Assistance via Video Streams	arXiv 2604	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-05	IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams	arXiv 2605	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-05	OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding	arXiv 2605	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-05	EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams	arXiv 2605	`Multimodal / Wearable` · `Personalization` · `Benchmark`
2026-05	MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory	arXiv 2605	`Memory` · `Multimodal / Wearable` · `Benchmark`
2026-05	PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration	arXiv 2605	`Embodied` · `Clarification` · `Long-horizon`
2026-07	Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos	ECCV 2026	`Multimodal / Wearable` · `Intervention Timing` · `Memory`
2026-07	ChatMuse: Supporting In-Person Small-Group Conversation Experience with a Proactive Assistive AI Agent in Mixed Reality	UIST 2026	`Multimodal / Wearable` · `Collaboration` · `Human Factors`
2026-08	GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience	arXiv 2608	`Multimodal / Wearable` · `Memory` · `Intervention Timing`
2026-08	From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs	arXiv 2608	`Multimodal / Wearable` · `Safety & Consent` · `Benchmark`
2026-08	StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding	arXiv 2608	`Multimodal / Wearable` · `Long-horizon` · `Benchmark`
2026-08	MOSS-VL Technical Report	arXiv 2608	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-08	StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary	arXiv 2608	`Multimodal / Wearable` · `Intervention Timing` · `Memory`
2026-08	OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs	arXiv 2608	`Multimodal / Wearable` · `Dialogue` · `Benchmark`
2026-08	When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs	EMNLP 2026	`Multimodal / Wearable` · `Clarification` · `Benchmark`
2026-08	MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs	arXiv 2608	`Multimodal / Wearable` · `Safety & Consent` · `Benchmark`
2026-09	Time-Aware Assistive Navigation	ICRA 2026	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-09	Ambient @ EgoProactive 2026: Proactive Egocentric Assistance with Visually Grounded Supervision	ECCV 2026 Wearable AI Challenge	`Multimodal / Wearable` · `Intervention Timing` · `Optimization`
2026-09	Omni Interaction Agent Technical Report	arXiv 2609	`Multimodal / Wearable` · `Dialogue` · `Intervention Timing`
2026-09	Realtime-Venus: A Full-Duplex Interaction System with Asynchronous Delegation	arXiv 2609	`Multimodal / Wearable` · `Dialogue` · `Tool Use`
2026-09	Full-Duplex Speech Models Take the Floor When Asked, Not When Needed	arXiv 2609	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`

Benchmarks, Personalization and Optimization

Date	Title	Venue / Source	Tags
2025-08	ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents	ACL 2026	`Benchmark` · `Dialogue` · `Intent Inference`
2025-09	ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation	ICLR 2026	`Personalization` · `Simulation` · `Benchmark`
2025-10	Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents	arXiv 2510	`Benchmark` · `Intent Inference` · `Tool Use`
2025-10	AgentFold: Long-Horizon Web Agents with Proactive Context Folding	ICLR 2026	`Long-horizon` · `Memory` · `Tool Use`
2025-11	Training Proactive and Personalized LLM Agents	COLM 2026	`Personalization` · `Optimization` · `Simulation`
2025-11	Structured Uncertainty guided Clarification for LLM Agents	Findings of ACL 2026	`Clarification` · `Tool Use` · `Benchmark`
2026-02	Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization	ICML 2026	`Optimization` · `Human Factors` · `Safety & Consent`
2026-03	ProEvent: An Event-centric Benchmark for Proactive Agents	arXiv 2607 / ACL ARR 2026	`Benchmark` · `Long-horizon` · `Intervention Timing`
2026-04	SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization	arXiv 2604	`Optimization` · `Skill Learning` · `Memory`
2026-04	PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory	arXiv 2604	`Long-horizon` · `Memory` · `Intervention Timing`
2026-05	CogniFold: Always-On Proactive Memory via Cognitive Folding	arXiv 2605	`Memory` · `Intent Inference` · `Benchmark`
2026-05	MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation	arXiv 2605	`Optimization` · `Skill Learning` · `Memory`
2026-05	Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?	arXiv 2605	`Intervention Timing` · `Optimization` · `Tool Use`
2026-05	ProactBench: Beyond What The User Asked For	arXiv 2605	`Benchmark` · `Dialogue` · `Intent Inference`
2026-05	Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World	arXiv 2605	`Long-horizon` · `Benchmark` · `Tool Use`
2026-05	π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows	arXiv 2605	`Long-horizon` · `Intent Inference` · `Benchmark`
2026-05	VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions	arXiv 2605	`Long-horizon` · `Personalization` · `Memory`
2026-06	Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues	arXiv 2606	`Dialogue` · `Personalization` · `Benchmark`
2026-06	Communication Policy Evolution for Proactive LLM Agents	arXiv 2606	`Dialogue` · `Intervention Timing` · `Optimization`
2026-06	See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence	arXiv 2606	`Multimodal / Wearable` · `Intervention Timing` · `Benchmark`
2026-07	Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents	arXiv 2607	`Long-horizon` · `Memory` · `Intervention Timing`
2026-07	ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents	Findings of ACL 2026	`Memory` · `Dialogue` · `Benchmark`
2026-08	Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants	arXiv 2608	`Personalization` · `Intervention Timing` · `Optimization`
2026-08	VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?	arXiv 2608	`Long-horizon` · `Benchmark` · `Safety & Consent`
2026-08	Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper	Findings of EMNLP 2026	`Multimodal / Wearable` · `Optimization` · `Safety & Consent`
2026-09	RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation	arXiv 2609	`Recommendation` · `Benchmark` · `Safety & Consent`
2026-09	Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality	arXiv 2609 · Under review	`Personalization` · `Planning` · `Human Factors`
2026-09	New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models	arXiv 2609	`Benchmark` · `Planning` · `Tool Use`

Benchmarks

For detailed comparison, see BENCHMARKS.md.

Date	Benchmark	Paper	Environment	What it tests
2024-03	ProMISe	ProMISe	information-seeking dialogue	proactive clarification for intent resolution
2024-10	RealHumanEval	Need Help?	programming tasks	proactive IDE assistance with human users
2024-10	ProactiveBench	Proactive Agent	desktop activity events	proactive task prediction and acceptance
2025-03	OmniMMI	OmniMMI	continuous audio-visual streams	proactive alerts, turn-taking, and streaming interaction
2025-05	ContextAgentBench	ContextAgent	wearable sensory contexts	proactive service prediction and tool calling
2025-07	FingerTip 20K	FingerTip 20K	Android trajectories	proactive task suggestion and personalized execution
2025-08	ProactiveEval	ProactiveEval	proactive dialogue	target planning and dialogue guidance across six domains
2025-10	PROBE	Beyond Reactivity	web problem-solving tasks	bottleneck discovery and autonomous resolution
2025-11	UserVille	Training Proactive and Personalized LLM Agents	SWE and deep-research user simulation	productivity, proactivity and personalization under vague prompts
2025-11	ClarifyBench	Structured Uncertainty Guided Clarification	dynamic tool-calling tasks	decide which tool argument to clarify and when to stop asking
2026-01	ChronosBench	Long-term Task-oriented Agent	dynamic task environments	proactive long-term intent maintenance
2026-02	ProAgentBench	ProAgentBench	real workflow logs	when-to-assist and how-to-assist
2026-02	ProactiveMobile	ProactiveMobile	mobile device context	latent intent to executable API sequence
2026-03	ProEvent	ProEvent	future event tracking	proactive event maintenance and reminders
2026-03	PIRA-Bench	PIRA-Bench	continuous GUI screenshots	proactive GUI intent recommendation
2026-03	ProReady-QA	StreamReady	long streaming videos with annotated evidence windows	answer only after sufficient evidence appears and avoid both premature and delayed responses
2026-03	GUIDE	GUIDE	open-ended GUI workflow videos	behavior state, intent, and help prediction
2026-03	ProactiveBench (MLLM)	ProactiveBench / Trento	visual difficulty scenarios	MLLM proactive help-seeking from visual context
2026-05	IPIBench	IPIBench	streaming video, multi-turn	interactive proactive monitoring, task management, reactive-proactive coordination
2026-04	ProVoice-Bench	ProVoice-Bench	voice interaction streams	proactive voice intervention timing, over-triggering, monitoring
2026-04	Pare-Bench	Pare	multi-app FSM environment	active user simulation, intervention timing, multi-app execution
2026-04	KnowU-Bench	KnowU-Bench	Android emulator	personalization, proactive tasks, consent and rejection handling
2026-04	LatentNeeds-Bench	PASK	real speech transcripts over multi-turn sessions	detect latent demand, assist, or stay silent under latency constraints
2026-05	CogEval-Bench	CogniFold	streaming event memory	proactive concept emergence and cognitive-structure formation
2026-05	MemEye	MemEye	multimodal long-term memory	visual evidence granularity and temporal state reasoning
2026-05	ProCodeBench	Proactive Coding Assistants	real IDE traces	proactive coding intent prediction and sim-to-real evaluation
2026-05	ProactBench	Beyond What The User Asked For	synthetic multi-turn conversations	grounded unstated-need inference at emergent, critical, and recovery triggers
2026-05	OmniPro	OmniPro	continuous omni-modal video streams	autonomously decide when and what to report across multiple triggers
2026-05	EgoPro-Bench	EgoPro-Bench	egocentric streaming videos and user profiles	personalized interaction timing with explicit attention-or-silence labels
2026-05	Claw-Anything	Claw-Anything	months of cross-service and multi-device activity	anticipate needs and complete proactive personal-assistant tasks amid noise
2026-05	π-Bench	π-Bench	persistent personal workspaces	proactive hidden-intent resolution and checklist completion in long-horizon workflows
2026-05	ProActEval	Anticipate and Learn	proactive assistant scenarios	idle-time anticipation, evidence acquisition, user effort and hallucination reduction
2026-05	VitaBench 2.0	VitaBench 2.0	long-term user interaction sequences	preference extraction, memory use, updates, and proactive missing-information acquisition
2026-06	Ψ-Bench	Ψ-Bench	persuasive dialogue	persona-sensitive influencing with simulated clients and user profiles
2026-06	GuidanceSalesBench	See, Infer, Intervene	pre-interaction retail videos and customer-state manifests	select greet, elicit, inform, recommend, or hold
2026-07	ProACT Collaboration Bench	ProACT	multi-user collaboration	breakdown detection, intervention timing, and non-interruptiveness
2026-07	InquireBench	InquireMobile	mobile GUI	proactive confirmation before risky or uncertain actions
2026-07	AndroidIntent	PersonalAlign	long-term Android records	vague-intent resolution and instruction-free routine suggestions
2026-07	BSDD	CoLabScience	streaming biomedical discussions	when and how to contribute without disrupting collaborators
2026-07	ENPMR-Bench	ENPMR-Bench	emotional-support dialogue	latent emotional-need inference and proactive supportive-memory retrieval
2026-07	EgoServe	Vinci2	continuous egocentric video	when-and-whether assistance across four memory horizons
2026-07	Int-Bench	AI Assistants Overassist	simulated learners solving 1,500 problems	whether, when, and how much a tutor should intervene
2026-07	AskBench	When and What to Ask	interactive intent-deficient and false-premise QA	decide when and what to clarify without sacrificing task performance
2026-08	Active-SWE	Active-SWE	repository snapshots without issue reports	autonomous discovery and repair of single, multiple, and potential bugs
2026-08	SPRINT	From Sports to Safety	real sports videos	early hazard warning, cause grounding, and false-alarm control
2026-08	StreamArena	StreamArena	hour-scale audio-visual streams	proactive monitoring alongside perception, retrospection, and tool use
2026-08	VibeLifeBench	VibeLifeBench	simulated multi-week life tasks	autonomous act, ask, and stay-silent decisions under silent world changes and implicit constraints
2026-08	JarvisBench	JarvisBench	ongoing single- and multi-agent work	recognize consequential user-owned decisions, request judgment, and route it back to working agents
2026-08	Act2Intention Bench	Act2Intention	continuous mobile GUI trajectories	understand, predict, suggest, and execute the next user intention from action history
2026-08	StreamSoccer	StreamSoccer	continuous soccer video	causal commentary across current, recent, and historical scopes with rule-assisted mode-or-silence scheduling
2026-08	OmniAssistBench	OmniAssistBench	continuous assistant-style video interactions	guide a user through a goal, incorporate visual prompts, and delay responses until the target event
2026-08	Interactive Visual Grounding	When Seeing Is Not Enough	ambiguous visual references under multi-turn protocols	ask follow-up questions and synthesize acquired evidence to ground the target
2026-08	MMPCBench	MMPCBench	flawed multimodal user inputs	autonomously detect, diagnose, and repair errors without an extra prompt
2026-09	PROS-Bench	Beyond Instruction-Driven Editing	source papers paired with editable scientific posters	discover source-grounded problems, obtain user acceptance, repair native objects, and validate outcomes
2026-09	RPCBench	RPCBench	evidence-grounded recommendation requests with corrupted premises	proactively detect, localize, and handle premise failures without fabricating unsupported recommendations
2026-09	CONFLICTGUI	Do GUI Agents Know When Not to Act?	feasible and conflicting instructions grounded in GUI states	verify feasibility and terminate rather than over-comply when instructions or GUI evidence conflict
2026-09	CC-Mediation	CC-Mediation	ten-turn cross-cultural conflict dialogues	decide when to intervene and select a mediation strategy with persistent downstream benefit
2026-09	OR-Clarify	Ask Before You Optimize	partially specified operations-research requests with hidden formulation slots	ask only formulation-critical questions, avoid silent assumptions, and stop when ready to model
2026-09	TIMELI	Time-Aware Assistive Navigation	egocentric navigation videos and closed-loop urban simulation	decide when to give concise guidance or remain silent for safety
2026-09	IdeaAMBIG	IdeaAMBIG	incomplete research-method specifications grounded in papers and code	detect implementation-critical gaps and issue clarification actions instead of assuming
2026-09	Physical Experiment Selection	New Evidence, Same Choice	controlled visual-physics measurements with known experiment costs	answer when evidence is sufficient or select the cheapest resolving experiment
2026-09	ProMediConv	ProMediConv	multi-stage legal dispute dialogues reconstructed from real cases	select mediation strategies proactively and improve party behavior over the trajectory

Tag Vocabulary

Tags are intentionally compact and reusable. They describe the paper's main contribution, not every detail.

Tag	Meaning
`Definition`	Defines or reframes proactive agents, proactive dialogue, or design-space boundaries.
`Survey`	Synthesizes a broad proactive-agent subfield or taxonomy.
`Human Factors`	Studies interruption, control, satisfaction, workload, adoption, or developer experience.
`Trust`	Focuses on competence perception, calibrated reliance, or trustworthy interaction.
`Safety & Consent`	Covers confirmation, autonomy boundaries, reversibility, rejection, or risk control.
`Privacy`	Centers privacy management, data minimization, or personal-context governance.
`Intervention Timing`	Focuses on when an agent should act, ask, suggest, or remain silent.
`Intent Inference`	Infers latent goals, hidden constraints, future tasks, or missing information.
`Clarification`	Proactively asks questions before planning, execution, or recommendation.
`Dialogue`	Proactive behavior in conversational, persuasive, or task-oriented interaction.
`Planning`	Proactive decomposition, task planning, scheduling, or future-state reasoning.
`Tool Use`	Tool calling, API execution, GUI operation, or action orchestration.
`Recommendation`	Proactive recommendation or suggestion ranking.
`Collaboration`	Multi-party or human-agent collaborative problem solving.
`Education`	Learning, tutoring, reflection, or student engagement contexts.
`Long-horizon`	Multi-session, dynamic, future-event, or long-running task maintenance.
`Personalization`	User preferences, personas, profiles, long-term user history, or user-specific adaptation.
`Memory`	Persistent memory, episodic memory, visual memory, skill memory, or cognitive memory structures.
`Simulation`	User simulation, environment simulation, synthetic users, or synthetic workflows.
`Optimization`	RL, reward modeling, multi-objective optimization, self-evolution, or behavior tuning.
`Skill Learning`	Skill creation, skill internalization, skill memory, or reusable procedure learning.
`Benchmark`	Introduces a dataset, evaluation suite, benchmark, simulator, or diagnostic protocol.
`Real-world Data`	Uses real user traces, field-study data, or deployment-like logs.
`Desktop`	Desktop activity streams, workstation context, or event logs.
`GUI`	Graphical interface agents, browser/app screens, or visual UI interaction.
`Mobile`	Mobile GUI, Android/iOS workflows, phone sensors, or mobile user context.
`OS`	Operating-system agents, cross-app workflows, or OS-level verification.
`IDE`	Programming assistants, code editors, or developer tooling.
`Multimodal / Wearable`	Video, audio, AR, smart glasses, egocentric streams, or open-world sensory context.
`Sensing`	Active context acquisition, sensor selection, or on-demand sensory capture.
`Embodied`	Robots, physical environments, or human-populated embodied settings.

Contributing

Pull requests are welcome.

Before adding a paper, check that it satisfies at least one of:

It predicts latent user intent before a complete explicit instruction.
It decides when to intervene, ask, suggest, execute, remind, or stay silent.
It evaluates proactive assistance, interruption cost, user control, consent, or personalization.
It contributes a benchmark or dataset where proactivity is the primary task.

Suggested note template:

# Paper Title

## Why It Matters

...

## Proactivity Signal

...

## Evaluation Setup

...

## Key Limitations

...

## Use For

...

Maintained by Low Entropy AI.

agent

ai-agent

awesome-list

benchmark

llm

multimodal

proactive

proactive-agent

Similar repos

trycua/acu

A curated list of resources about AI agents for Computer Use, including research papers, projects,…

1,770

showlab/Awesome-GUI-Agent

💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

1,216

opendilab/awesome-ui-agents

A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond…

319

MobileLLM/Personal_LLM_Agents_Survey

Paper list for Personal LLM Agents

435

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

3,121

Bingo-W/Awesome-Agent-Search

[Survey] Agent and Tool Search: Foundations, Techniques, and Open Challenges

AGI-Edgerunners/LLM-Agents-Papers

A repo lists papers related to LLM based agent

2,347

WILLOSCAR/Awesome-HCI-LLM

Awesome-HCI （Ubiquitous, LLM, MLLM, Agent, RAG, Embodied-AI, RLHF)

Contributors

Kaiming-Y

32 commits

KashiwaByte

2 commits

peanutfestival

1 commits

LowEntropyAI/awesome-proactive-agent

README

Awesome Proactive Agents

Companion Guides

Contents

Scope

Must Read

Papers

Foundations, Surveys and Human Factors

Proactive Interaction and Planning

GUI, Mobile, OS and Coding Agents

Multimodal, Wearable and Embodied Agents

Benchmarks, Personalization and Optimization

Benchmarks

Tag Vocabulary

Contributing

Contributors

Similar repos

LowEntropyAI/awesome-proactive-agent

README

Awesome Proactive Agents

Companion Guides

Contents

Scope

Must Read

Papers

Foundations, Surveys and Human Factors

Proactive Interaction and Planning

GUI, Mobile, OS and Coding Agents

Multimodal, Wearable and Embodied Agents

Benchmarks, Personalization and Optimization

Benchmarks

Tag Vocabulary

Contributing

Similar repos

Contributors