LiteResearcher-4B-SFT

This is the SFT cold-start checkpoint for LiteResearcher — a scalable agentic RL training framework for deep-research agents.

It is the initial policy used to launch the two-stage curriculum RL training that produces the final simplex-ai-inc/LiteResearcher-4B model.

If you are looking for the final RL model, please use simplex-ai-inc/LiteResearcher-4B. If you want to reproduce the RL training from scratch, this is the checkpoint you need.

Model details

• Base model: Qwen/Qwen3-4B-Thinking-2507
• Architecture: Qwen3ForCausalLM (36 layers, hidden 2560, 32 heads, GQA 8 KV heads)
• Max position embeddings: 262,144 (RoPE θ = 5,000,000)
• Precision: bfloat16
• Total params: ~4B
• Training framework: LLaMA-Factory

Training recipe

The SFT trajectories teach the model the ReAct think → search → visit → answer loop and the strict <answer>...</answer> output contract used by the RL environment. Because the base is the Thinking-2507 variant, the model preserves long chain-of-thought behavior inside <think>...</think> blocks, which is what the downstream RL curriculum builds on.

How to use

As the initial policy for RL (recommended use)

# In the LiteResearcher training scripts (Training/ folder of the repo)
export MODEL_PATH=$(hf download simplex-ai-inc/LiteResearcher-4B-SFT \
                                --local-dir ./literesearcher_sft)

Then follow the Stage-1 / Stage-2 RL instructions in the LiteResearcher repository.

Stand-alone inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "simplex-ai-inc/LiteResearcher-4B-SFT"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

The model expects the same ReAct system prompt and tool schema used by LiteResearcher (see Inference/ in the repo).

Citation

If you use this checkpoint in academic work, please cite the LiteResearcher project — see the GitHub README for the BibTeX entry.

License

Apache-2.0, inheriting from the Qwen3-4B-Thinking-2507 base model.