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}
}