Elamur Research
☰
home / papers / 2025 / Search-o1: Agentic Search-Enhanced Large Reasoning Models

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/2025.emnlp-main.276.pdf

Summary

Large reasoning models (LRMs) such as OpenAI-o1 or QwQ produce long chains of thought, and those chains often run into gaps in what the model knows. The authors measure this through hedging words: on GPQA diamond, QwQ-32B-Preview writes "perhaps" about 30 times per answer. Search-o1 addresses this without extra training. The model is prompted to write its own search queries whenever it gets stuck while reasoning, and it can search again as many times as it needs within one session. Retrieved web documents tend to be long and noisy, so a separate Reason-in-Documents step first checks them against the current query and the reasoning so far. Only a short, relevant result goes back into the chain. The authors test it on reasoning tasks in science, math and coding, and on six open-domain QA benchmarks. Search-o1 beats direct reasoning, standard RAG and agentic RAG baselines, and its overall GPQA score is higher than that of human experts. The work shows that letting LRMs use tools while they answer can make them more reliable, and it points toward deep-research systems.

Key points

  • Approach: two parts on top of an LRM, driven by prompts rather than fine-tuning. The first is an agentic RAG loop in which the model decides when to search and what to search for. The second is Reason-in-Documents, which filters retrieved text before it enters the reasoning chain. Code: github.com/RUC-NLPIR/Search-o1.
  • GPQA extended set vs. human experts: Search-o1 scores 57.9 overall, 68.7 in physics and 69.5 in biology. It still trails chemists in chemistry (40.7 vs. 72.6).
  • Open-domain QA (NQ, TriviaQA, HotpotQA, 2WikiMultihopQA, MuSiQue, Bamboogle; EM/F1): on multi-hop tasks, average EM is 29.6% higher than RAG-QwQ-32B and 5.3% higher than RAgent-QwQ-32B. On single-hop tasks, agentic search gives QwQ-32B almost no gain.
  • Retrieval depth and backbones: with just one retrieved document, Search-o1 already beats direct reasoning and standard RAG that use ten. The gains also hold with Sky-T1-32B-Preview and DeepSeek-R1-Distill-Qwen-32B as backbones.
  • Limitations the authors state: search is the only tool so far, with no training-based (fine-tuning or RL) optimisation, and multimodal models are not yet covered.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Natural language processing

Cited by

157 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 153 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.276

@inproceedings{li2025search,
  title = {{Search-o1: Agentic Search-Enhanced Large Reasoning Models}},
  author = {Li, Xiaoxi and Dong, Guanting and Jin, Jiajie and Zhang, Yuyao and Zhou, Yujia and Zhu, Yutao and Zhang, Peitian and Dou, Zhicheng},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.276},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.276}
}

References

57 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024a. Huatuogpt-o1, towards medical complex reasoning with llms. arXiv preprint arXiv:2412.18925. find
  2. Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, and Dong Yu. 2024b. Do not think that much for 2+3=? on the overthinking of o1-like llms. Preprint, arXiv:2412.21187. find our card
  3. Kahneman Daniel. 2017. Thinking, fast and slow. find
  4. Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, and Ji-Rong Wen. 2025a. Tool-star: Empowering llm-brained multi-tool reasoner via reinforcement learning. CoRR, abs/2505.16410. — [arXiv:2505.16410](https://arxiv.org/abs/2505.16410) find
  5. Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou. 2025b. Self-play with execution feedback: Improving instruction-following capabilities of large language models. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, A… find
  6. Guanting Dong, Hangyu Mao, Kai Ma, Licheng Bao, Yifei Chen, Zhongyuan Wang, Zhongxia Chen, Jiazhen Du, Huiyang Wang, Fuzheng Zhang, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou. 2025c. Agentic reinforced policy optimization. Preprint, arXiv:2507.19849. — [arXiv:2507.19849](https://arxiv.org/abs/2507.19849) find
  7. Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2024. How abilities in large language models are affected by supervised fine-tuning data composition. In Proceedings of the 62nd Annual Meeting of the Association for… find
  8. Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou, and Ji-Rong Wen. 2025d. Progressive multimodal reasoning via active retrieval. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27… find
  9. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783. find
  10. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. find
  11. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948. find our card
  12. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the MATH dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets an… find our card
  13. Tom Henighan, Jared Kaplan, Mor Katz, Mark Chen, Christopher Hesse, Jacob Jackson, Heewoo Jun, Tom B Brown, Prafulla Dhariwal, Scott Gray, et al. 2020. Scaling laws for autoregressive generative modeling. arXiv preprint arXiv:2010.14701. find
  14. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing A multi-hop QA dataset for comprehensive evaluation of reasoning steps. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, p… find our card
  15. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Kai Dang, An Yang, Rui Men, Fei Huang, Xingzhang Ren, Xuancheng Ren, Jingren Zhou, and Junyang Lin. 2024. Qwen2.5-coder technical report. CoRR, abs/2409.12186. find our card
  16. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276. find our card
  17. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720. find our card
  18. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. CoRR, abs/2403.07974. find our card
  19. Jinhao Jiang, Zhipeng Chen, Yingqian Min, Jie Chen, Xiaoxue Cheng, Jiapeng Wang, Yiru Tang, Haoxiang Sun, Jia Deng, Wayne Xin Zhao, et al. 2024. Technical report: Enhancing llm reasoning with reward-guided tree search. arXiv preprint arXiv:2411.11694. — [arXiv:2411.11694](https://arxiv.org/abs/2411.11694) find
  20. Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, and Zhicheng Dou. 2025a. Hierarchical document refinement for long-context retrieval-augmented generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume… find
  21. Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Zhao Yang, Hongjin Qian, and Zhicheng Dou. 2025b. Decoupled planning and execution: A hierarchical reasoning framework for deep search. CoRR, abs/2507.02652. — [arXiv:2507.02652](https://arxiv.org/abs/2507.02652) find
  22. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension. In ACL, pages 1601–1611, Vancouver, Canada. Association for Computational Linguistics. find our card
  23. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistic… find our card
  24. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474. find
  25. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay V. Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, and Vedant Misra. 2022. Solving quantitative reasoning problems with language models. In Advances in… find our card
  26. Xiaoxi Li, Zhicheng Dou, Yujia Zhou, and Fangchao Liu. 2024. Corpuslm: Towards a unified language model on corpus for knowledge-intensive tasks. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington DC, USA, July 14… find
  27. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou. 2025a. Webthinker: Empowering large reasoning models with deep research capability. CoRR, abs/2504.21776. find
  28. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Ye Qi, and Zhicheng Dou. 2025b. Retrollm: Empowering large language models to retrieve fine-grained evidence within generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape… find
  29. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, Yutao Zhu, and Zhicheng Dou. 2025c. From matching to generation: A survey on generative information retrieval. ACM Trans. Inf. Syst., 43(3):83:1– 83:62. find
  30. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Rev… find our card
  31. Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Raghavi Chandu, Chandra Bhagavatula, and Yejin Choi. 2024. The unlocking spell on base llms: Rethinking alignment via in-context learning. In The Twelfth International Conference on Learning Representations, ICLR… find our card
  32. Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, and Hao Su. 2023. Deductive verification of chain-of-thought reasoning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, L… find our card
  33. Jingyu Liu, Jiaen Lin, and Yong Liu. 2024. How much can RAG help the reasoning of llm? CoRR, abs/2410.02338. find
  34. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67. find
  35. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2023. GPQA: A graduate-level google-proof q&a benchmark. CoRR, abs/2311.12022. find our card
  36. Jiejun Tan, Zhicheng Dou, Yutao Zhu, Peidong Guo, Kun Fang, and Ji-Rong Wen. 2024. Small models, big insights: Leveraging slim proxy models to decide when and what to retrieve for llms. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… find
  37. Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. find
  38. Wenhan Liu, Xinyu Ma, Weiwei Sun, Yutao Zhu, Yuchen Li, Dawei Yin, and Zhicheng Dou. 2025. Reasonrank: Empowering passage ranking with strong reasoning ability. Preprint, arXiv:2508.07050. find
  39. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. find
  40. Yingqian Min, Zhipeng Chen, Jinhao Jiang, Jie Chen, Jia Deng, Yiwen Hu, Yiru Tang, Jiapeng Wang, Xiaoxue Cheng, Huatong Song, et al. 2024. Imitate, explore, and self-improve: A reproduction report on slow-thinking reasoning systems. arXiv preprint arXiv:2412.09413. find
  41. Jiaan Wang, Fandong Meng, Yunlong Liang, and Jie Zhou. 2024. Drt-o1: Optimized deep reasoning translation via long chain-of-thought. arXiv preprint arXiv:2412.17498. — [arXiv:2412.17498](https://arxiv.org/abs/2412.17498) find
  42. OpenAI. 2024. Learning to reason with llms. find
  43. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A. Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 5687–5711. Association for Comp… find
  44. Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, et al. 2024. O1 replication journey: A strategic progress report–part 1. arXiv preprint arXiv:2410.18982. find
  45. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng… find
  46. Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query expansion with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 9414–9423. Association for Computational Linguistics. find our card
  47. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837. find our card
  48. Ken C. L. Wong, Hongzhi Wang, Etienne E. Vos, Bianca Zadrozny, Campbell D. Watson, and Tanveer F. Syeda-Mahmood. 2021. Addressing deep learning model uncertainty in long-range climate forecasting with late fusion. CoRR, abs/2112.05254. — [arXiv:2112.05254](https://arxiv.org/abs/2112.05254) find
  49. Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, and Yanghua Xiao. 2024. How easily do irrelevant inputs skew the responses of large language models? Preprint, arXiv:2404.03302. find
  50. Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2024a. RE-COMP: improving retrieval-augmented lms with context compression and selective augmentation. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find
  51. Guowei Xu, Peng Jin, Li Hao, Yibing Song, Lichao Sun, and Li Yuan. 2024b. Llava-o1: Let vision language models reason step-by-step. arXiv preprint arXiv:2411.10440. find
  52. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In EMNLP, pages 2369–2380, Brussels, Belgium. Association for Computational Linguistics. find our card
  53. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. find our card
  54. Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2024. Making retrieval-augmented language models robust to irrelevant context. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find our card
  55. Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin, Bo Wang, Shimin Li, Yunhua Zhou, Qipeng Guo, Xuanjing Huang, and Xipeng Qiu. 2024. Scaling of search and learning: A roadmap to reproduce o1 from reinforcement learning perspective. arXiv preprint arXiv:2412.14135. find
  56. Yuxiang Zhang, Shangxi Wu, Yuqi Yang, Jiangming Shu, Jinlin Xiao, Chao Kong, and Jitao Sang. 2024. o1-coder: an o1 replication for coding. arXiv preprint arXiv:2412.00154. — [arXiv:2412.00154](https://arxiv.org/abs/2412.00154) find
  57. Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025. Processbench: Identifying process errors in mathematical reasoning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… find our card