library_name, license, base_model, tags, language, pipeline_tag

library_name	license	base_model	tags	language	pipeline_tag
transformers	apache-2.0	Qwen/Qwen2.5-3B-Instruct	qwen2.5 deepcontrol search-augmented reinforcement-learning text-generation	en	text-generation

DeepControl-Qwen2.5-3B

Deep search agent checkpoint from Qwen2.5-3B-Instruct under Adaptive Information Control for Search-Augmented LLM Reasoning (EMNLP 2026).

Quick start

See our repo DeepControl for more details.

Recommended Configuration:

Setting	Value
Inference dtype	BF16
Context length	8,192
Generation temperature	0
Maximum new tokens per action	512
Maximum agent turns	8
Retrieval top-k	5
Retrieval corpus	Wikipedia 2018 (wiki18)

For example, the model server can be started with:

vllm serve sxiong/DeepControl-Qwen2.5-3B \
  --dtype bfloat16 \
  --max-model-len 8192

Loading the model alone does not provide retrieval. It requires the DeepControl system prompt, action parser, and wiki18 corpus.

Citation

@article{xiong2026adaptive,
  title={Adaptive Information Control for Search-Augmented LLM Reasoning},
  author={Xiong, Siheng and Gungordu, Oguzhan and Kerce, James C and Fekri, Faramarz},
  journal={arXiv preprint arXiv:2602.01672},
  year={2026}
}