---
title: "Enhancing LLM-based Search Agents via Contribution Weighted"
description: "The authors propose CW-GRPO, which keeps the group-relative outcome advantage of standard GRPO (exact-match reward… 48 references."
authors: ["Junzhe Wang", "Zhiheng Xi", "Yajie Yang", "Hao Luo", "Shihan Dou", "Tao Gui", "Qi Zhang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1462/"
doi: "10.18653/v1/2026.acl-long.1462"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2026-enhancing-llm-based-search-agents/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-enhancing-llm-based-search-agents/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/) / Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization

# Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization

**Authors:** [Junzhe Wang](https://md.research.elamur.ai/free/en/authors/junzhe-wang/), [Zhiheng Xi](https://md.research.elamur.ai/free/en/authors/zhiheng-xi/), Yajie Yang, [Hao Luo](https://md.research.elamur.ai/free/en/authors/hao-luo/), [Shihan Dou](https://md.research.elamur.ai/free/en/authors/shihan-dou/), [Tao Gui](https://md.research.elamur.ai/free/en/authors/tao-gui/) and [Qi Zhang](https://md.research.elamur.ai/free/en/authors/qi-zhang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1462/) · [PDF](https://aclanthology.org/2026.acl-long.1462.pdf) · [DOI 10.18653/v1/2026.acl-long.1462](https://doi.org/10.18653/v1/2026.acl-long.1462) · [OpenAlex](https://openalex.org/W7166809132)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Search agents built on LLMs learn to query external engines during multi-round reasoning, but reinforcement learning for such agents faces a dilemma. Rewarding intermediate steps needs a learned critic, which tends to be unstable. Rewarding only the final answer makes it hard to tell which search rounds actually helped. The authors propose CW-GRPO, which keeps the group-relative outcome advantage of standard GRPO (exact-match reward, no value network) and adds round-level credit assignment. A frozen LLM judge, guided by a rubric, labels every round of a trajectory with two binary signals: whether the retrieved documents added new, relevant evidence, and whether the reasoning in that round was sound. These signals are combined into a contribution weight. The weight then rescales the trajectory's advantage across its rounds rather than serving as a separate reward. Across several knowledge-intensive QA benchmarks, CW-GRPO beats both outcome- and process-supervised baselines. The work shows a stable way to inject process-level feedback into outcome-based RL for agents.

## Key points
- Compared with plain GRPO, CW-GRPO yields relative gains of 5.0% on Qwen3-8B and 6.3% on Qwen3-1.7B.
- A round counts as contributive only when it passes both checks (retrieval utility and reasoning correctness). This conjunctive gate is designed to filter out judge noise.
- In successful trajectories, contribution tends to cluster in a few informative rounds rather than being spread evenly across the search.
- Limitations:
  - Advantages are redistributed only for successful trajectories, so failed ones get no per-round attribution.
  - Credit is assigned per round, not per token.
  - The method depends on an external LLM judge, which adds inference cost.
- Code is released at github.com/zsxmwjz/CW-GRPO.

*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

- [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) — University, Shanghai, China · 167 works · 20,987 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

## Cite

Cite as: Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui and Qi Zhang. 2026. Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wang2026enhancing,
  title = {{Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization}},
  author = {Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui and Qi Zhang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1462},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1462}
}
```

- [← previous Enhancing Lexical Relation Mining with Structured Sememe Knowledge](https://md.research.elamur.ai/free/en/papers/wang-2026-enhancing-lexical-relation-mining-structured/)
- [next → Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion](https://md.research.elamur.ai/free/en/papers/park-2026-enhancing-multilingual-rag-systems-debiased/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/)

## References

48 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. OpenAI: Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, and 105 others. 2025. [gpt-oss-120b &…](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/)
2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [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 The Twelfth International Conference on Learning Representations.
3. DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, and 245 others. 2025. [Deepseek-v3.2: Pushing the frontier of open…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/)
4. Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. [Re2g: Retrieve, rerank, generate](https://md.research.elamur.ai/free/en/papers/glass-2022-re2g-retrieve-rerank-generate/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages…
5. Google. 2025. Gemini 3 pro model card. Technical report, Google DeepMind. Accessed: 2026-01-06. [find](https://scholar.google.com/scholar?q=Google%2E+2025%2E+Gemini+3+pro+model+card%2E+Technical+report%2C+Google+DeepMind%2E+Accessed%3A+2026%2D01%2D06%2E)
6. 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](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). Preprint, arXiv:2103.03874.
7. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [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/). Preprint, arXiv:2011.01060.
8. Hui Huang, Xingyuan Bu, Hongli Zhou, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, and Tiejun Zhao. 2025. An empirical study of LLM-as-a-judge for LLM evaluation: Fine-tuned judge model is not a general substitute for GPT-4. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5… [find](https://scholar.google.com/scholar?q=Hui+Huang%2C+Xingyuan+Bu%2C+Hongli+Zhou%2C+Yingqi+Qu%2C+Jing+Liu%2C+Muyun+Yang%2C+Bing+Xu%2C+and+Tiejun+Zhao%2E+2025%2E+An+empirical+study+of+LLM%2Das%2Da%2Djudge+for+LLM+evaluation%3A+Fine%2Dtuned+judge+model+is+not+a+general+s)
9. Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. [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, Singapore. Association fo…
10. Bowen Jin, Jinsung Yoon, Priyanka Kargupta, Sercan O. Arik, and Jiawei Han. 2025a. An empirical study on reinforcement learning for reasoning-search interleaved llm agents. Preprint, arXiv:2505.15117. — [arXiv:2505.15117](https://arxiv.org/abs/2505.15117) [find](https://scholar.google.com/scholar?q=Bowen+Jin%2C+Jinsung+Yoon%2C+Priyanka+Kargupta%2C+Sercan+O%2E+Arik%2C+and+Jiawei+Han%2E+2025a%2E+An+empirical+study+on+reinforcement+learning+for+reasoning%2Dsearch+interleaved+llm+agents%2E+Preprint%2C+arXiv%3A2505%2E15117%2E)
11. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025b. [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/). Preprint, arXiv:2503.09516.
12. Mandar Joshi, Eunsol Choi, Daniel S. Weld, and Luke Zettlemoyer. 2017. [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/). Preprint, arXiv:1705.03551.
13. Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron Courville, and Nicolas Le Roux. 2025. Vineppo: Refining credit assignment in rl training of llms. Preprint, arXiv:2410.01679. [find](https://scholar.google.com/scholar?q=Amirhossein+Kazemnejad%2C+Milad+Aghajohari%2C+Eva+Portelance%2C+Alessandro+Sordoni%2C+Siva+Reddy%2C+Aaron+Courville%2C+and+Nicolas+Le+Roux%2E+2025%2E+Vineppo%3A+Refining+credit+assignment+in+rl+training+of+llms%2E+Prepri)
14. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/)
15. Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. 2022. [Webgpt: Browser-assisted question-answering with human feedback](https://md.research.elamur.ai/free/en/papers/nakano-2021-webgpt-browser-assisted-question-answering/). Preprint, arXiv:2112.09332.
16. 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, pages 5687–5711. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+A+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computati)
17. Kunal Sawarkar, Abhilasha Mangal, and Shivam Raj Solanki. 2024. Blended rag: Improving rag (retriever-augmented generation) accuracy with semantic search and hybrid query-based retrievers. In 2024 IEEE 7th international conference on multimedia information processing and retrieval (MIPR), pages 155–… [find](https://scholar.google.com/scholar?q=Kunal+Sawarkar%2C+Abhilasha+Mangal%2C+and+Shivam+Raj+Solanki%2E+2024%2E+Blended+rag%3A+Improving+rag+%28retriever%2Daugmented+generation%29+accuracy+with+semantic+search+and+hybrid+query%2Dbased+retrievers%2E+In+2024+IEE)
18. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). Preprint, arXiv:2501.05366.
19. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. Preprint, arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+Preprint%2C+arXiv%3A1707%2E06347%2E)
20. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, Yutao Zhu, and Zhicheng Dou. 2025b. From matching to generation: A survey on generative information retrieval. ACM Transactions on Information Systems, 43(3):1–62. [find](https://scholar.google.com/scholar?q=Xiaoxi+Li%2C+Jiajie+Jin%2C+Yujia+Zhou%2C+Yuyao+Zhang%2C+Peitian+Zhang%2C+Yutao+Zhu%2C+and+Zhicheng+Dou%2E+2025b%2E+From+matching+to+generation%3A+A+survey+on+generative+information+retrieval%2E+ACM+Transactions+on+Inform)
21. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [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/). Preprint, arXiv:2402.03300.
22. Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, and Xipeng Qiu. 2025c. R3-rag: Learning step-by-step reasoning and retrieval for llms via reinforcement learning. arXiv preprint arXiv:2505.23794. [find](https://scholar.google.com/scholar?q=Yuan+Li%2C+Qi+Luo%2C+Xiaonan+Li%2C+Bufan+Li%2C+Qinyuan+Cheng%2C+Bo+Wang%2C+Yining+Zheng%2C+Yuxin+Wang%2C+Zhangyue+Yin%2C+and+Xipeng+Qiu%2E+2025c%2E+R3%2Drag%3A+Learning+step%2Dby%2Dstep+reasoning+and+retrieval+for+llms+via+reinfor)
23. Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). Preprint, arXiv:2305.20050.
24. Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, and Xuanjing Huang. 2026. Mm-doc-r1: Training agents for long document visual question answering through multi-turn reinforcement learnin… [find](https://scholar.google.com/scholar?q=Jiahang+Lin%2C+Kai+Hu%2C+Binghai+Wang%2C+Yuhao+Zhou%2C+Zhiheng+Xi%2C+Honglin+Guo%2C+Shichun+Liu%2C+Junzhe+Wang%2C+Shihan+Dou%2C+Enyu+Zhou%2C+Hang+Yan%2C+Zhenhua+Han%2C+Tao+Gui%2C+Qi+Zhang%2C+and+Xuanjing+Huang%2E+2026%2E+Mm%2Ddoc%2Dr1%3A+)
25. Jiacai Liu, Chaojie Wang, Chris Yuhao Liu, Liang Zeng, Rui Yan, Yiwen Sun, Yang Liu, and Yahui Zhou. 2024. Improving multi-step reasoning abilities of large language models with direct advantage policy optimization. Preprint, arXiv:2412.18279. — [arXiv:2412.18279](https://arxiv.org/abs/2412.18279) [find](https://scholar.google.com/scholar?q=Jiacai+Liu%2C+Chaojie+Wang%2C+Chris+Yuhao+Liu%2C+Liang+Zeng%2C+Rui+Yan%2C+Yiwen+Sun%2C+Yang+Liu%2C+and+Yahui+Zhou%2E+2024%2E+Improving+multi%2Dstep+reasoning+abilities+of+large+language+models+with+direct+advantage+polic)
26. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. Preprint, arXiv:2212.10511. [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem)
27. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). arXiv preprint arXiv: 2…
28. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, and 465 others. 2025… — [OpenAI GPT-5 System Card](https://md.research.elamur.ai/free/en/papers/singh-2025-openai-gpt-5-system-card/)
29. Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. [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/). Preprint, arXiv:2503.05592.
30. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
31. Qwen Team. 2025a. Qwen3-max: Just scale it. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2025a%2E+Qwen3%2Dmax%3A+Just+scale+it%2E)
32. Qwen Team. 2025b. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
33. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Multi-hop questions via single-hop question composition. Preprint, arXiv:2108.00573. — [arXiv:2108.00573](https://arxiv.org/abs/2108.00573) [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+Musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Preprint%2C+arXiv%3A2108%2E00573%2E+%E2%80%94+%5BarXiv%3A2108%2E00573%5D%28htt)
34. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
35. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. [Solving math word problems with process-and outcome-based feedback](https://md.research.elamur.ai/free/en/papers/uesato-2022-solving-math-word-problems-process/). arXiv preprint arXiv:2211.14275.
36. Hongru Wang, Cheng Qian, Wanjun Zhong, Xiusi Chen, Jiahao Qiu, Shijue Huang, Bowen Jin, Mengdi Wang, Kam-Fai Wong, and Heng Ji. 2025a. Acting less is reasoning more! teaching model to act efficiently. Preprint, arXiv:2504.14870. — [arXiv:2504.14870](https://arxiv.org/abs/2504.14870) [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Cheng+Qian%2C+Wanjun+Zhong%2C+Xiusi+Chen%2C+Jiahao+Qiu%2C+Shijue+Huang%2C+Bowen+Jin%2C+Mengdi+Wang%2C+Kam%2DFai+Wong%2C+and+Heng+Ji%2E+2025a%2E+Acting+less+is+reasoning+more%21+teaching+model+to+act+efficiently%2E)
37. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). arXiv preprint arXiv:2212.03533.
38. Ziliang Wang, Xuhui Zheng, Kang An, Cijun Ouyang, Jialu Cai, Yuhang Wang, and Yichao Wu. 2025b. Stepsearch: Igniting llms search ability via stepwise proximal policy optimization. Preprint, arXiv:2505.15107. — [arXiv:2505.15107](https://arxiv.org/abs/2505.15107) [find](https://scholar.google.com/scholar?q=Ziliang+Wang%2C+Xuhui+Zheng%2C+Kang+An%2C+Cijun+Ouyang%2C+Jialu+Cai%2C+Yuhang+Wang%2C+and+Yichao+Wu%2E+2025b%2E+Stepsearch%3A+Igniting+llms+search+ability+via+stepwise+proximal+policy+optimization%2E+Preprint%2C+arXiv%3A2505)
39. Quan Wei, Siliang Zeng, Chenliang Li, William Brown, Oana Frunza, Wei Deng, Anderson Schneider, Yuriy Nevmyvaka, Yang Katie Zhao, Alfredo Garcia, and Mingyi Hong. 2025. Reinforcing multi-turn reasoning in llm agents via turn-level reward design. Preprint, arXiv:2505.11821. — [arXiv:2505.11821](https://arxiv.org/abs/2505.11821) [find](https://scholar.google.com/scholar?q=Quan+Wei%2C+Siliang+Zeng%2C+Chenliang+Li%2C+William+Brown%2C+Oana+Frunza%2C+Wei+Deng%2C+Anderson+Schneider%2C+Yuriy+Nevmyvaka%2C+Yang+Katie+Zhao%2C+Alfredo+Garcia%2C+and+Mingyi+Hong%2E+2025%2E+Reinforcing+multi%2Dturn+reasonin)
40. Zhiheng Xi, Jixuan Huang, Chenyang Liao, Baodai Huang, Honglin Guo, Jiaqi Liu, Rui Zheng, Junjie Ye, Jiazheng Zhang, Wenxiang Chen, Wei He, Yiwen Ding, Guanyu Li, Zehui Chen, Zhengyin Du, Xuesong Yao, Yufei Xu, Jiecao Chen, Tao Gui, and 4 others. 2025. Agentgym-rl: Training llm agents for long-horiz… — [arXiv:2509.08755](https://arxiv.org/abs/2509.08755) [find](https://scholar.google.com/scholar?q=Zhiheng+Xi%2C+Jixuan+Huang%2C+Chenyang+Liao%2C+Baodai+Huang%2C+Honglin+Guo%2C+Jiaqi+Liu%2C+Rui+Zheng%2C+Junjie+Ye%2C+Jiazheng+Zhang%2C+Wenxiang+Chen%2C+Wei+He%2C+Yiwen+Ding%2C+Guanyu+Li%2C+Zehui+Chen%2C+Zhengyin+Du%2C+Xuesong+Yao%2C)
41. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. [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/). Preprint, arXiv:1809.09600.
42. Ying, Yue Zhang, Zhangyue Yin, Zhiheng Xi, and 4 others. 2026. Opennovelty: An llm-powered agentic system for verifiable scholarly novelty assessment. Preprint, arXiv:2601.01576. — [arXiv:2601.01576](https://arxiv.org/abs/2601.01576) [find](https://scholar.google.com/scholar?q=Ying%2C+Yue+Zhang%2C+Zhangyue+Yin%2C+Zhiheng+Xi%2C+and+4+others%2E+2026%2E+Opennovelty%3A+An+llm%2Dpowered+agentic+system+for+verifiable+scholarly+novelty+assessment%2E+Preprint%2C+arXiv%3A2601%2E01576%2E+%E2%80%94+%5BarXiv%3A2601%2E01576%5D%28)
43. Wenlin Zhang, Xiaopeng Li, Yingyi Zhang, Pengyue Jia, Yichao Wang, Huifeng Guo, Yong Liu, and Xiangyu Zhao. 2025a. Deep research: A survey of autonomous research agents. arXiv preprint arXiv:2508.12752. — [arXiv:2508.12752](https://arxiv.org/abs/2508.12752) [find](https://scholar.google.com/scholar?q=Wenlin+Zhang%2C+Xiaopeng+Li%2C+Yingyi+Zhang%2C+Pengyue+Jia%2C+Yichao+Wang%2C+Huifeng+Guo%2C+Yong+Liu%2C+and+Xiangyu+Zhao%2E+2025a%2E+Deep+research%3A+A+survey+of+autonomous+research+agents%2E+arXiv+preprint+arXiv%3A2508%2E1275)
44. Yaocheng Zhang, Haohuan Huang, Zijun Song, Yuanheng Zhu, Qichao Zhang, Zijie Zhao, and Dongbin Zhao. 2025b. [Criticsearch: Fine-grained credit assignment for search agents via a retrospective critic](https://md.research.elamur.ai/free/en/papers/zhang-2026-criticsearch-fine-grained-credit-assignment/). Preprint, arXiv:2511.12159.
45. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, and Bin Cui. 2026. [Retrieval-augmented generation for ai-generated content: A survey](https://md.research.elamur.ai/free/en/papers/zhao-2024-retrieval-augmented-generation-ai-generated/). Data Science and Engineering, pages 1–29.
46. Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2024. [Sglang: Efficient execution of structured language model programs](https://md.research.elamur.ai/free/en/papers/zheng-2023-sglang-efficient-execution-structured-language/). In Advances in Neural Information Processing System…
47. Yujia Zhou, Yan Liu, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Zheng Liu, Chaozhuo Li, Zhicheng Dou, Tsung-Yi Ho, and Philip S Yu. 2024. Trustworthiness in retrieval-augmented generation systems: A survey. arXiv preprint arXiv:2409.10102. — [arXiv:2409.10102](https://arxiv.org/abs/2409.10102) [find](https://scholar.google.com/scholar?q=Yujia+Zhou%2C+Yan+Liu%2C+Xiaoxi+Li%2C+Jiajie+Jin%2C+Hongjin+Qian%2C+Zheng+Liu%2C+Chaozhuo+Li%2C+Zhicheng+Dou%2C+Tsung%2DYi+Ho%2C+and+Philip+S+Yu%2E+2024%2E+Trustworthiness+in+retrieval%2Daugmented+generation+systems%3A+A+survey%2E)
48. Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, Xun Wang, Lin Sun, Xiangzheng Zhang, and Sujian Li. 2025. Chain-of-thought matters: improving long-context language models with reasoning path supervision. arXiv preprint arXiv:2502.20790. [find](https://scholar.google.com/scholar?q=Dawei+Zhu%2C+Xiyu+Wei%2C+Guangxiang+Zhao%2C+Wenhao+Wu%2C+Haosheng+Zou%2C+Junfeng+Ran%2C+Xun+Wang%2C+Lin+Sun%2C+Xiangzheng+Zhang%2C+and+Sujian+Li%2E+2025%2E+Chain%2Dof%2Dthought+matters%3A+improving+long%2Dcontext+language+models+w)

*Updated 1 November 2026*