Research

Paper

AI LLM February 23, 2026

How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1

Authors

Yinuo Xu, Shuo Lu, Jianjie Cheng, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He, Jian Liang

Abstract

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain underexplored. To fully understand the role of RL, we conduct a systematic study along three decoupled dimensions: prompt template, reward function, and policy optimization. Our study reveals that: 1) the Fast Thinking template yields greater stability and better performance than the Slow Thinking template used in prior work; 2) the F1-based reward underperforms the EM due to training collapse driven by answer avoidance; this can be mitigated by incorporating action-level penalties, ultimately surpassing EM; 3) REINFORCE outperforms PPO while requiring fewer search actions, whereas GRPO shows the poorest stability among policy optimization methods. Building on these insights, we then introduce Search-R1++, a strong baseline that improves the performance of Search-R1 from 0.403 to 0.442 (Qwen2.5-7B) and 0.289 to 0.331 (Qwen2.5-3B). We hope that our findings can pave the way for more principled and reliable RL training strategies in Deep Research systems.

Metadata

arXiv ID: 2602.19526
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-02-23
Fetched: 2026-02-24 04:38

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19526v1</id>\n    <title>How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1</title>\n    <updated>2026-02-23T05:33:17Z</updated>\n    <link href='https://arxiv.org/abs/2602.19526v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19526v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain underexplored. To fully understand the role of RL, we conduct a systematic study along three decoupled dimensions: prompt template, reward function, and policy optimization. Our study reveals that: 1) the Fast Thinking template yields greater stability and better performance than the Slow Thinking template used in prior work; 2) the F1-based reward underperforms the EM due to training collapse driven by answer avoidance; this can be mitigated by incorporating action-level penalties, ultimately surpassing EM; 3) REINFORCE outperforms PPO while requiring fewer search actions, whereas GRPO shows the poorest stability among policy optimization methods. Building on these insights, we then introduce Search-R1++, a strong baseline that improves the performance of Search-R1 from 0.403 to 0.442 (Qwen2.5-7B) and 0.289 to 0.331 (Qwen2.5-3B). We hope that our findings can pave the way for more principled and reliable RL training strategies in Deep Research systems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-02-23T05:33:17Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Yinuo Xu</name>\n    </author>\n    <author>\n      <name>Shuo Lu</name>\n    </author>\n    <author>\n      <name>Jianjie Cheng</name>\n    </author>\n    <author>\n      <name>Meng Wang</name>\n    </author>\n    <author>\n      <name>Qianlong Xie</name>\n    </author>\n    <author>\n      <name>Xingxing Wang</name>\n    </author>\n    <author>\n      <name>Ran He</name>\n    </author>\n    <author>\n      <name>Jian Liang</name>\n    </author>\n  </entry>"
}