---
title: "ZeroSearch — paper by Sun et al. (2025) — summary and ideas"
description: "It offers a cheaper and more controllable path to search-capable agents, although hosting the… 47 references, cited by 50 papers here."
authors: ["Hao Sun", "Zile Qiao", "Jiayan Guo", "Xuanbo Fan", "Yingyan Hou", "Yong Jiang", "Pengjun Xie", "Yan Zhang", "Fei Huang", "Jingren Zhou"]
year: 2025
venue: "arXiv:2505.04588"
source: "https://arxiv.org/abs/2505.04588"
doi: "10.48550/arxiv.2505.04588"
arxiv: "2505.04588"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sun-2025-zerosearch-incentivize-search-capability-llms/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2025-zerosearch-incentivize-search-capability-llms/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / ZeroSearch: Incentivize the Search Capability of LLMs without Searching

# ZeroSearch: Incentivize the Search Capability of LLMs without Searching

**Authors:** [Hao Sun](https://md.research.elamur.ai/free/en/authors/hao-sun/), [Zile Qiao](https://md.research.elamur.ai/free/en/authors/zile-qiao/), [Jiayan Guo](https://md.research.elamur.ai/free/en/authors/jiayan-guo/), [Xuanbo Fan](https://md.research.elamur.ai/free/en/authors/xuanbo-fan/), Yingyan Hou, [Yong Jiang](https://md.research.elamur.ai/free/en/authors/yong-jiang/), [Pengjun Xie](https://md.research.elamur.ai/free/en/authors/pengjun-xie/), [Yan Zhang](https://md.research.elamur.ai/free/en/authors/yan-zhang/), [Fei Huang](https://md.research.elamur.ai/free/en/authors/fei-huang/) and [Jingren Zhou](https://md.research.elamur.ai/free/en/authors/jingren-zhou/) · **Year:** 2025 · **Venue:** arXiv:2505.04588 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2505.04588) · [PDF](https://arxiv.org/pdf/2505.04588) · [DOI 10.48550/arxiv.2505.04588](https://doi.org/10.48550/arxiv.2505.04588) · [arXiv 2505.04588](https://arxiv.org/abs/2505.04588) · [OpenAlex](https://openalex.org/W4417092508)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [50](https://md.research.elamur.ai/free/en/papers/sun-2025-zerosearch-incentivize-search-capability-llms/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Training LLM agents to use web search through reinforcement learning usually means querying a live engine during rollouts. This is costly, since it can take hundreds of thousands of API calls, and the returned documents vary unpredictably in quality. ZeroSearch, from Tongyi Lab (Alibaba Group), removes the real engine from training. First, a separate LLM gets light supervised fine-tuning so it can act as a search simulator. Changing a few prompt words makes it return either helpful or deliberately noisy documents. During RL, this frozen simulator answers the policy's queries. A curriculum steadily raises the share of noisy results, so the policy first learns the interaction format and then learns to reason when retrieval is poor. Across seven question-answering benchmarks, a 3B simulator already teaches useful search behavior. A 7B simulator matches training with Google Search, and a 14B one exceeds it. The method works for base and instruction-tuned policies of different sizes and with several RL algorithms. It offers a cheaper and more controllable path to search-capable agents, although hosting the simulator still requires GPU servers.

## Key points
- Simulator sizes from 3B to 14B were compared. Fine-tuned simulators (SFT-7B, SFT-14B) clearly beat prompt-only simulators, and quality grows with model size. SFT-7B is on par with Google Search, and SFT-14B surpasses it.
- The policy follows a multi-turn template with `<think>`, `<search>`, `<information>` and `<answer>` tags, as in Search-R1, so no separate supervised warm-up is needed.
- Evaluation covers NQ, TriviaQA, PopQA, HotpotQA, 2Wiki, MuSiQue and Bamboogle. With Qwen-2.5-3B-Base, the average scores are REINFORCE 34.47, GRPO 33.17 and PPO 32.67.
- The easy-to-hard curriculum beats a fixed 0.5 noise probability. Averages are 34.47 vs. 32.59 for Qwen-2.5-3B-Base and 36.07 vs. 34.84 for LLaMA-3.2-3B-Base.
- Training incurs zero search API cost, and throughput scales with added GPUs. The stated limitation is the infrastructure cost of serving the simulator LLM.

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

## Institutions

- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 201 works · 17,173 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Hao Sun, Zile Qiao, Jiayan Guo, Xuanbo Fan, Yingyan Hou, Yong Jiang, Pengjun Xie, Yan Zhang, Fei Huang and Jingren Zhou. 2025. ZeroSearch: Incentivize the Search Capability of LLMs without Searching. arXiv:2505.04588.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{sun2025zerosearch,
  title = {{ZeroSearch: Incentivize the Search Capability of LLMs without Searching}},
  author = {Hao Sun, Zile Qiao, Jiayan Guo, Xuanbo Fan, Yingyan Hou, Yong Jiang, Pengjun Xie, Yan Zhang, Fei Huang and Jingren Zhou},
  year = {2025},
  doi = {10.48550/arxiv.2505.04588},
  eprint = {2505.04588},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2505.04588}
}
```

- [← previous WebDancer: Towards Autonomous Information Seeking Agency](https://md.research.elamur.ai/free/en/papers/wu-2025-webdancer-towards-autonomous-information-seeking/)
- [next → HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://md.research.elamur.ai/free/en/papers/hu-2025-hiagent-hierarchical-working-memory-management/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

47 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In International conference on learning representations, volume 2024, pages 9112–9141, 2024.
2. B. Bohnet, V. Q. Tran, P. Verga, R. Aharoni, D. Andor, L. B. Soares, M. Ciaramita, J. Eisenstein, K. Ganchev, J. Herzig, et al. [Attributed question answering: Evaluation and modeling for attributed large language models](https://md.research.elamur.ai/free/en/papers/bohnet-2022-attributed-question-answering-evaluation-modeling/). arXiv preprint arXiv:2212.08037, 2022.
3. M. Chen, L. Sun, T. Li, H. Sun, C. Zhu, H. Wang, J. Pan, W. Zhang, H. Chen, F. Yang, et al. Learning to reason with search for llms via reinforcement learning. Advances in Neural Information Processing Systems, 38:85287–85307, 2026. [find](https://scholar.google.com/scholar?q=M%2E+Chen%2C+L%2E+Sun%2C+T%2E+Li%2C+H%2E+Sun%2C+C%2E+Zhu%2C+H%2E+Wang%2C+J%2E+Pan%2C+W%2E+Zhang%2C+H%2E+Chen%2C+F%2E+Yang%2C+et+al%2E+Learning+to+reason+with+search+for+llms+via+reinforcement+learning%2E+Advances+in+Neural+Information+Processin)
4. A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, P. Barham, H. W. Chung, C. Sutton, S. Gehrmann, et al. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). arXiv preprint arXiv:2204.02311, 2022.
5. W. Feng, C. Hao, Y. Zhang, J. Song, and H. Wang. Airrag: Activating intrinsic reasoning for retrieval augmented generation via tree-based search. arXiv preprint arXiv:2501.10053, 2025. — [arXiv:2501.10053](https://arxiv.org/abs/2501.10053) [find](https://scholar.google.com/scholar?q=W%2E+Feng%2C+C%2E+Hao%2C+Y%2E+Zhang%2C+J%2E+Song%2C+and+H%2E+Wang%2E+Airrag%3A+Activating+intrinsic+reasoning+for+retrieval+augmented+generation+via+tree%2Dbased+search%2E+arXiv+preprint+arXiv%3A2501%2E10053%2C+2025%2E+%E2%80%94+%5BarXiv%3A2501%2E1)
6. L. Gao, Z. Dai, P. Pasupat, A. Chen, A. T. Chaganty, Y. Fan, V. Zhao, N. Lao, H. Lee, D.-C. Juan, et al. [Rarr: Researching and revising what language models say, using language models](https://md.research.elamur.ai/free/en/papers/gao-2023-rarr-researching-revising-what-language/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
7. A. Grattafiori, A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Vaughan, et al. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783, 2024.
8. D. Guo, D. Yang, H. Zhang, J. Song, P. Wang, Q. Zhu, R. Xu, R. Zhang, S. Ma, X. Bi, et al. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025.
9. X. Ho, A.-K. D. Nguyen, S. Sugawara, and A. Aizawa. [Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, 2020.
10. S. Imani, L. Du, and H. Shrivastava. [Mathprompter: Mathematical reasoning using large language models](https://md.research.elamur.ai/free/en/papers/imani-2023-mathprompter-mathematical-reasoning-large-language/). arXiv preprint arXiv:2303.05398, 2023.
11. A. Jaech, A. Kalai, A. Lerer, A. Richardson, A. El-Kishky, A. Low, A. Helyar, A. Madry, A. Beutel, A. Carney, et al. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720, 2024.
12. S. Jeong, J. Baek, S. Cho, S. J. Hwang, and J. C. Park. [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://md.research.elamur.ai/free/en/papers/jeong-2024-adaptive-rag-learning-adapt-retrieval/). arXiv preprint arXiv:2403.14403, 2024.
13. Z. Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, E. Ishii, Y. J. Bang, A. Madotto, and P. Fung. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM computing surveys, 55(12):1–38, 2023.
14. J. Jiang, J. Chen, J. Li, R. Ren, S. Wang, W. X. Zhao, Y. Song, and T. Zhang. [Rag-star: Enhancing deliberative reasoning with retrieval augmented verification and refinement](https://md.research.elamur.ai/free/en/papers/jiang-2025-rag-star-enhancing-deliberative-reasoning/). arXiv preprint arXiv:2412.12881, 2024.
15. J. Jiang, Z. Chen, Y. Min, J. Chen, X. Cheng, J. Wang, Y. Tang, H. Sun, J. Deng, W. X. Zhao, et al. Technical report: Enhancing llm reasoning with reward-guided tree search. arXiv preprint arXiv:2411.11694, 2024. — [arXiv:2411.11694](https://arxiv.org/abs/2411.11694) [find](https://scholar.google.com/scholar?q=J%2E+Jiang%2C+Z%2E+Chen%2C+Y%2E+Min%2C+J%2E+Chen%2C+X%2E+Cheng%2C+J%2E+Wang%2C+Y%2E+Tang%2C+H%2E+Sun%2C+J%2E+Deng%2C+W%2E+X%2E+Zhao%2C+et+al%2E+Technical+report%3A+Enhancing+llm+reasoning+with+reward%2Dguided+tree+search%2E+arXiv+preprint+arXiv%3A2411%2E)
16. Z. Jiang, F. F. Xu, L. Gao, Z. Sun, Q. Liu, J. Dwivedi-Yu, Y. Yang, J. Callan, and G. Neubig. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992, 2023.
17. B. Jin, H. Zeng, Z. Yue, J. Yoon, S. Arik, D. Wang, H. Zamani, and J. Han. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). arXiv preprint arXiv:2503.09516, 2025.
18. M. Joshi, E. Choi, D. S. Weld, and L. Zettlemoyer. [Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, 2017.
19. T. Kwiatkowski, J. Palomaki, O. Redfield, M. Collins, A. Parikh, C. Alberti, D. Epstein, I. Polosukhin, J. Devlin, K. Lee, et al. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguistics, 7:453–466, 2019.
20. A. Lewkowycz, A. Andreassen, D. Dohan, E. Dyer, H. Michalewski, V. Ramasesh, A. Slone, C. Anil, I. Schlag, T. Gutman-Solo, et al. [Solving quantitative reasoning problems with language models](https://md.research.elamur.ai/free/en/papers/lewkowycz-2022-solving-quantitative-reasoning-problems-language/). Advances in Neural Information Processing Systems, 35:3843–3857, 2022.
21. X. Li, G. Dong, J. Jin, Y. Zhang, Y. Zhou, Y. Zhu, P. Zhang, and Z. Dou. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). arXiv preprint arXiv:2501.05366, 2025.
22. X. Li, J. Jin, G. Dong, H. Qian, Y. Wu, J.-R. Wen, Y. Zhu, and Z. Dou. [Webthinker: Empowering large reasoning models with deep research capability](https://md.research.elamur.ai/free/en/papers/li-2025-webthinker-empowering-large-reasoning-models/). Advances in Neural Information Processing Systems, 38:120091–120131, 2026.
23. X. Li, J. Jin, Y. Zhou, Y. Wu, Z. Li, Q. Ye, and Z. Dou. [Retrollm: Empowering large language models to retrieve fine-grained evidence within generation](https://md.research.elamur.ai/free/en/papers/li-2025-retrollm-empowering-large-language-models/). arXiv preprint arXiv:2412.11919, 2024.
24. X. Li, W. Xu, R. Zhao, F. Jiao, S. Joty, and L. Bing. [Can we further elicit reasoning in llms? critic-guided planning with retrieval-augmentation for solving challenging tasks](https://md.research.elamur.ai/free/en/papers/li-2025-can-we-further-elicit-reasoning/). arXiv preprint arXiv:2410.01428, 2024.
25. A. Mallen, A. Asai, V. Zhong, R. Das, D. Khashabi, and H. Hajishirzi. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers), pages 98… [find](https://scholar.google.com/scholar?q=A%2E+Mallen%2C+A%2E+Asai%2C+V%2E+Zhong%2C+R%2E+Das%2C+D%2E+Khashabi%2C+and+H%2E+Hajishirzi%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+memories%2E+In+Proceedings+of+the+61)
26. J. Menick, M. Trebacz, V. Mikulik, J. Aslanides, F. Song, M. Chadwick, M. Glaese, S. Young, L. Campbell-Gillingham, G. Irving, et al. [Teaching language models to support answers with verified quotes](https://md.research.elamur.ai/free/en/papers/menick-2022-teaching-language-models-support-answers/). arXiv preprint arXiv:2203.11147, 2022.
27. O. Press, M. Zhang, S. Min, L. Schmidt, N. A. Smith, and M. Lewis. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5687–5711, 2023. [find](https://scholar.google.com/scholar?q=O%2E+Press%2C+M%2E+Zhang%2C+S%2E+Min%2C+L%2E+Schmidt%2C+N%2E+A%2E+Smith%2C+and+M%2E+Lewis%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EM)
28. O. Ram, Y. Levine, I. Dalmedigos, D. Muhlgay, A. Shashua, K. Leyton-Brown, and Y. Shoham. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). Transactions of the Association for Computational Linguistics, 11:1316–1331, 2023.
29. H. Rashkin, V. Nikolaev, M. Lamm, L. Aroyo, M. Collins, D. Das, S. Petrov, G. S. Tomar, I. Turc, and D. Reitter. [Measuring attribution in natural language generation models](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/). Computational Linguistics, 49(4):777–840, 2023.
30. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017. [find](https://scholar.google.com/scholar?q=J%2E+Schulman%2C+F%2E+Wolski%2C+P%2E+Dhariwal%2C+A%2E+Radford%2C+and+O%2E+Klimov%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2C+2017%2E)
31. Z. Shao, P. Wang, Q. Zhu, R. Xu, J. Song, X. Bi, H. Zhang, M. Zhang, Y. Li, Y. Wu, et al. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300, 2024.
32. W. Shi, S. Min, M. Yasunaga, M. Seo, R. James, M. Lewis, L. Zettlemoyer, and W.-t. Yih. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). arXiv preprint arXiv:2301.12652, 2023.
33. K. Shuster, S. Poff, M. Chen, D. Kiela, and J. Weston. [Retrieval augmentation reduces hallucination in conversation](https://md.research.elamur.ai/free/en/papers/shuster-2021-retrieval-augmentation-reduces-hallucination-conversation/). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3784–3803, 2021.
34. H. Song, J. Jiang, Y. Min, J. Chen, Z. Chen, W. X. Zhao, L. Fang, and J.-R. Wen. [R1-searcher: Incentivizing the search capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/song-2025-r1-searcher-incentivizing-search/). arXiv preprint arXiv:2503.05592, 2025.
35. R. Taylor, M. Kardas, G. Cucurull, T. Scialom, A. Hartshorn, E. Saravia, A. Poulton, V. Kerkez, and R. Stojnic. [Galactica: A large language model for science](https://md.research.elamur.ai/free/en/papers/taylor-2022-galactica-large-language-model-science/). arXiv preprint arXiv:2211.09085, 2022.
36. H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal. Musique: Multihop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554, 2022. — [♫ MuSiQue: Multihop Questions via Single-hop Question Composition](https://md.research.elamur.ai/free/en/papers/trivedi-2022-musique-multihop-questions-single-hop/)
37. R. J. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229–256, 1992. [find](https://scholar.google.com/scholar?q=R%2E+J%2E+Williams%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%3A229%E2%80%93256%2C+1992%2E)
38. S. Xia, X. Li, Y. Liu, T. Wu, and P. Liu. [Evaluating mathematical reasoning beyond accuracy](https://md.research.elamur.ai/free/en/papers/xia-2024-evaluating-mathematical-reasoning-accuracy/). arXiv preprint arXiv:2404.05692, 2024.
39. R. Yamauchi, S. Sonoda, A. Sannai, and W. Kumagai. Lpml: llm-prompting markup language for mathematical reasoning. arXiv preprint arXiv:2309.13078, 2023. — [arXiv:2309.13078](https://arxiv.org/abs/2309.13078) [find](https://scholar.google.com/scholar?q=R%2E+Yamauchi%2C+S%2E+Sonoda%2C+A%2E+Sannai%2C+and+W%2E+Kumagai%2E+Lpml%3A+llm%2Dprompting+markup+language+for+mathematical+reasoning%2E+arXiv+preprint+arXiv%3A2309%2E13078%2C+2023%2E+%E2%80%94+%5BarXiv%3A2309%2E13078%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F230)
40. A. Yang, B. Yang, B. Zhang, B. Hui, B. Zheng, B. Yu, C. Li, D. Liu, F. Huang, H. Wei, et al. Qwen2.5 technical report. arXiv preprint arXiv:2412.15115, 2024. [find](https://scholar.google.com/scholar?q=A%2E+Yang%2C+B%2E+Yang%2C+B%2E+Zhang%2C+B%2E+Hui%2C+B%2E+Zheng%2C+B%2E+Yu%2C+C%2E+Li%2C+D%2E+Liu%2C+F%2E+Huang%2C+H%2E+Wei%2C+et+al%2E+Qwen2%2E5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2C+2024%2E)
41. Z. Yang, P. Qi, S. Zhang, Y. Bengio, W. Cohen, R. Salakhutdinov, and C. D. Manning. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In Proceedings of the 2018 conference on empirical methods in natural language processing, pages 2369–2380, 2018.
42. O. Yoran, T. Wolfson, B. Bogin, U. Katz, D. Deutch, and J. Berant. [Answering questions by meta-reasoning over multiple chains of thought](https://md.research.elamur.ai/free/en/papers/yoran-2023-answering-questions-meta-reasoning-over/). arXiv preprint arXiv:2304.13007, 2023.
43. W. Yu, D. Iter, S. Wang, Y. Xu, M. Ju, S. Sanyal, C. Zhu, M. Zeng, and M. Jiang. [Generate rather than retrieve: Large language models are strong context generators](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/). arXiv preprint arXiv:2209.10063, 2022.
44. J. Zhang, Z. Li, K. Das, B. Malin, and S. Kumar. [Sac3: reliable hallucination detection in black-box language models via semantic-aware cross-check consistency](https://md.research.elamur.ai/free/en/papers/zhang-2023-sac3-reliable-hallucination-detection-black/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15445–15458, 2023.
45. W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, et al. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223, 2023.
46. Y. Zhao, H. Yin, B. Zeng, H. Wang, T. Shi, C. Lyu, L. Wang, W. Luo, and K. Zhang. [Marco-o1: Towards open reasoning models for open-ended solutions](https://md.research.elamur.ai/free/en/papers/zhao-2024-marco-o1-towards-open-reasoning/). arXiv preprint arXiv:2411.14405, 2024.
47. Y. Zheng, D. Fu, X. Hu, X. Cai, L. Ye, P. Lu, and P. Liu. [Deepresearcher: Scaling deep research via reinforcement learning in real-world environments](https://md.research.elamur.ai/free/en/papers/zheng-2025-deepresearcher-scaling-deep-research-reinforcement/). arXiv preprint arXiv:2504.03160, 2025. *Figure 3: Reward curve comparison between Z ERO S EARCH and Search-R1(using a real search engine).* *Figure 4…

*Updated 2 November 2026*