We argue that efficient agentic reasoning benefits from decomposing deliberation into three interacting systems: reactive execution (System I) for fine-grained reasoning and direct action; simulative reasoning (System II) that predicts consequences of proposed actions through a world model; and self-regulation (System III) that decides *when* and *how deeply* to plan through a learned configurator.
14
11 commits
1 linked in READMEs
updated May 22, 2026
README
SR²AM-v1.0-30B
We argue that efficient agentic reasoning benefits from decomposing deliberation into three interacting systems: reactive execution (System I) for fine-grained reasoning and direct action; simulative reasoning (System II) that predicts consequences of proposed actions through a world model; and self-regulation (System III) that decides when and how deeply to plan through a learned configurator.
SR²AM (Self-Regulated Simulative Reasoning Agentic LLM) is our instantiation: the configurator and simulative planner are realized as distinct stages within an LLM's chain-of-thought reasoning, with the LLM itself serving as the world model in language space.
SR²AM-v1.0-30B achieves an overall Pass@1 of 71.3 across 11 benchmarks spanning math, science, tabular analysis, and web information seeking — competitive with systems at 685B–1T parameters, while consuming 25–95% fewer reasoning tokens than comparably sized agentic LLMs.
More details: project website | paper | GitHub.
Key Features
- System I + II + III decomposition: a configurator (System III) decides per-turn whether to plan, continue an existing plan, or act directly; a simulative planner (System II) constructs plans grounded in predicted future states; reactive execution (System I) handles fine-grained reasoning and tool use.
- SFT + RL training: supervised learning on data encoding the self-regulated planning structure, followed by reinforcement learning (GRPO) for task success.
- Agentic tool use: web search (SerpAPI), web browsing with LLM summarization, and stateless Python code execution (SandboxFusion).
- Reasoning efficiency: 5,518 reasoning tokens per trajectory on average — 51% fewer than MiroThinker-v1.5-30B and 95% fewer than ASearcher-Web-QWQ-v2 for comparable or better accuracy.
- RL learns to plan further, not more often: RL increases average planning horizon by 22.8% while planning frequency grows only 2.0 percentage points.
Quick Start
See the GitHub repository for setup and inference instructions.
Main Results
SR²AM-v1.0-30B sits above the size-vs-accuracy trendline in (a) and on the Pareto frontier of reasoning-token efficiency vs. accuracy among 30/32B models in (b). The full benchmark breakdown is in the paper.
Citation
@article{deng2026sr2am,
title={Efficient Agentic Reasoning Through Self-Regulated Simulative Planning},
author={Deng, Mingkai and Hou, Jinyu and Neves, Lara Sá and
Pimpalkhute, Varad and Killian, Taylor W. and
Liu, Zhengzhong and Xing, Eric P.},
journal={arXiv preprint arXiv:2605.22138},
year={2026}
}
License
Released under the Apache License 2.0.
Contributors
Similar repos
We argue that efficient agentic reasoning benefits from decomposing deliberation into three interacting systems: reactive execution (System I) for fine-grained reasoning and direct action; simulative reasoning (System II) that predicts consequences of proposed actions through a world model; and self-regulation (System III) that decides *when* and *how deeply* to plan through a learned configurator.
14
11 commits
1 linked in READMEs
updated May 22, 2026
README
SR²AM-v1.0-30B
We argue that efficient agentic reasoning benefits from decomposing deliberation into three interacting systems: reactive execution (System I) for fine-grained reasoning and direct action; simulative reasoning (System II) that predicts consequences of proposed actions through a world model; and self-regulation (System III) that decides when and how deeply to plan through a learned configurator.
SR²AM (Self-Regulated Simulative Reasoning Agentic LLM) is our instantiation: the configurator and simulative planner are realized as distinct stages within an LLM's chain-of-thought reasoning, with the LLM itself serving as the world model in language space.
SR²AM-v1.0-30B achieves an overall Pass@1 of 71.3 across 11 benchmarks spanning math, science, tabular analysis, and web information seeking — competitive with systems at 685B–1T parameters, while consuming 25–95% fewer reasoning tokens than comparably sized agentic LLMs.
More details: project website | paper | GitHub.
Key Features
- System I + II + III decomposition: a configurator (System III) decides per-turn whether to plan, continue an existing plan, or act directly; a simulative planner (System II) constructs plans grounded in predicted future states; reactive execution (System I) handles fine-grained reasoning and tool use.
- SFT + RL training: supervised learning on data encoding the self-regulated planning structure, followed by reinforcement learning (GRPO) for task success.
- Agentic tool use: web search (SerpAPI), web browsing with LLM summarization, and stateless Python code execution (SandboxFusion).
- Reasoning efficiency: 5,518 reasoning tokens per trajectory on average — 51% fewer than MiroThinker-v1.5-30B and 95% fewer than ASearcher-Web-QWQ-v2 for comparable or better accuracy.
- RL learns to plan further, not more often: RL increases average planning horizon by 22.8% while planning frequency grows only 2.0 percentage points.
Quick Start
See the GitHub repository for setup and inference instructions.
Main Results
SR²AM-v1.0-30B sits above the size-vs-accuracy trendline in (a) and on the Pareto frontier of reasoning-token efficiency vs. accuracy among 30/32B models in (b). The full benchmark breakdown is in the paper.
Citation
@article{deng2026sr2am,
title={Efficient Agentic Reasoning Through Self-Regulated Simulative Planning},
author={Deng, Mingkai and Hou, Jinyu and Neves, Lara Sá and
Pimpalkhute, Varad and Killian, Taylor W. and
Liu, Zhengzhong and Xing, Eric P.},
journal={arXiv preprint arXiv:2605.22138},
year={2026}
}
License
Released under the Apache License 2.0.