---
title: "Adversarial Yet Cooperative — paper by Xu et al. (2026)"
description: "The authors propose ARR (Adversarial Reasoning RAG), which splits the work between two agents. 35 references."
authors: ["Can Xu", "Lingyong Yan", "Jiayi Wu", "Haosen Wang", "Shuaiqiang Wang", "Yuchen Li", "Jizhou Huang", "Dawei Yin", "Xiang Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1868/"
doi: "10.18653/v1/2026.findings-acl.1868"
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/xu-2026-adversarial-yet-cooperative-multi-perspective/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-adversarial-yet-cooperative-multi-perspective/)

[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/21/) / Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

# Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

**Authors:** [Can Xu](https://md.research.elamur.ai/free/en/authors/can-xu/), [Lingyong Yan](https://md.research.elamur.ai/free/en/authors/lingyong-yan/), [Jiayi Wu](https://md.research.elamur.ai/free/en/authors/jiayi-wu/), [Haosen Wang](https://md.research.elamur.ai/free/en/authors/haosen-wang/), [Shuaiqiang Wang](https://md.research.elamur.ai/free/en/authors/shuaiqiang-wang/), [Yuchen Li](https://md.research.elamur.ai/free/en/authors/yuchen-li/), [Jizhou Huang](https://md.research.elamur.ai/free/en/authors/jizhou-huang/), [Dawei Yin](https://md.research.elamur.ai/free/en/authors/dawei-yin/) and [Xiang Li](https://md.research.elamur.ai/free/en/authors/xiang-li/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.1868/) · [PDF](https://aclanthology.org/2026.findings-acl.1868.pdf) · [DOI 10.18653/v1/2026.findings-acl.1868](https://doi.org/10.18653/v1/2026.findings-acl.1868) · [OpenAlex](https://openalex.org/W7166859416)

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

## Summary
Most agentic RAG systems rely on one model that both searches and reasons. When retrieved documents are incomplete or contradictory, that single viewpoint can reinforce its own mistakes. Training on final-answer rewards also cannot tell sound reasoning from a lucky guess. The authors propose ARR (Adversarial Reasoning RAG), which splits the work between two agents. A Reasoner queries a search engine and builds an answer, while a Verifier challenges its logic using the retrieved evidence. Both agents are trained jointly with GRPO. Training uses two signals: an adversarial outcome reward, which makes the agents compete on correctness, and a token-level process-aware advantage for the Verifier. The second signal needs no external reward model. It favors confident, evidence-backed feedback that lowers the Reasoner's policy entropy, reflecting the idea that good RAG reasoning moves from uncertainty toward a settled answer. On general and multi-hop QA benchmarks drawn from FlashRAG, ARR beats Search-R1 and other baselines on Qwen2.5-3B, Qwen2.5-7B and Qwen3-8B. The paper shows that structured disagreement between two agents can make retrieval-based reasoning more reliable.

## Key points
- Average gains over the second-best baseline are:
  - Qwen2.5-3B: +11.1% EM and +7.6% F1
  - Qwen2.5-7B: +9.5% EM and +7.8% F1
  - Qwen3-8B: +13.4% EM and +9.8% F1
- Multi-hop results: on Musique, EM gains over the runner-up are 26.1%, 12.0% and 23.9% across the three backbones. On HotpotQA, ARR reaches EM 0.455 (7B) and 0.506 (8B).
- ARR often beats Search-R1 even when Search-R1 gets two attempts (pass@2). With Qwen3-8B, it reaches EM 0.472 on NQ and 0.506 on HotpotQA, about 10% and 11.5% higher. A 3B ARR model outperforms 7B baselines on general QA.
- Ablation shows the process-aware advantage matters most. Removing it drops Musique F1 from 27.3 to 21.9 on Qwen2.5-7B. Removing the adversarial outcome reward causes a smaller but consistent decline.
- Setup and limitations: training runs on VeRL and vLLM, with the two agents on separate GPU groups, which wastes some compute. Evaluation covers only English short-answer QA, so results may not transfer to long-form generation.

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

📚 Shelves (6): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin and Xiang Li. 2026. Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{xu2026adversarial,
  title = {{Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models}},
  author = {Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin and Xiang Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1868},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1868}
}
```

- [← previous Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards](https://md.research.elamur.ai/free/en/papers/xie-2026-advancing-reasoning-diffusion-language-models/)
- [next → AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM](https://md.research.elamur.ai/free/en/papers/yang-2026-aea-adaptive-expert-allocation-improves/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/21/)

## References

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

1. Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen. 2025a. [Research: Learning to reason with search for llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/chen-2025-research-learning-reason-search-llms/).
2. Zhipeng Chen, Xiaobo Qin, Youbin Wu, Yue Ling, Qinghao Ye, Wayne Xin Zhao, and Guang Shi. 2025b. Pass@k training for adaptively balancing exploration and exploitation of large reasoning models. [find](https://scholar.google.com/scholar?q=Zhipeng+Chen%2C+Xiaobo+Qin%2C+Youbin+Wu%2C+Yue+Ling%2C+Qinghao+Ye%2C+Wayne+Xin+Zhao%2C+and+Guang+Shi%2E+2025b%2E+Pass%40k+training+for+adaptively+balancing+exploration+and+exploitation+of+large+reasoning+models%2E)
3. Ganqu Cui, Yuchen Zhang, Jiacheng Chen, Lifan Yuan, Zhi Wang, Yuxin Zuo, Haozhan Li, Yuchen Fan, Huayu Chen, Weize Chen, Zhiyuan Liu, Hao Peng, Lei Bai, Wanli Ouyang, Yu Cheng, Bowen Zhou, and Ning Ding. 2025. [The entropy mechanism of reinforcement learning for reasoning language models](https://md.research.elamur.ai/free/en/papers/cui-2025-entropy-mechanism-reinforcement-learning-reasoning/).
4. Yong Deng, Guoqing Wang, Zhenzhe Ying, Xiaofeng Wu, Jinzhen Lin, Wenwen Xiong, Yuqin Dai, Shuo Yang, Zhanwei Zhang, Qiwen Wang, Yang Qin, Yuan Wang, Quanxing Zha, Sunhao Dai, and Changhua Meng. 2025. Atom-searcher: Enhancing agentic deep research via fine-grained atomic thought reward. [find](https://scholar.google.com/scholar?q=Yong+Deng%2C+Guoqing+Wang%2C+Zhenzhe+Ying%2C+Xiaofeng+Wu%2C+Jinzhen+Lin%2C+Wenwen+Xiong%2C+Yuqin+Dai%2C+Shuo+Yang%2C+Zhanwei+Zhang%2C+Qiwen+Wang%2C+Yang+Qin%2C+Yuan+Wang%2C+Quanxing+Zha%2C+Sunhao+Dai%2C+and+Changhua+Meng%2E+2025%2E+)
5. Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025. [Retool: Reinforcement learning for strategic tool use in llms](https://md.research.elamur.ai/free/en/papers/feng-2025-retool-reinforcement-learning-strategic-tool/).
6. Daocheng Fu, Jianbiao Mei, Licheng Wen, Xuemeng Yang, Cheng Yang, Rong Wu, Tao Hu, Siqi Li, Yufan Shen, Xinyu Cai, Pinlong Cai, Botian Shi, Yong Liu, and Yu Qiao. 2025. Re-searcher: Robust agentic search with goal-oriented planning and self-reflection. [find](https://scholar.google.com/scholar?q=Daocheng+Fu%2C+Jianbiao+Mei%2C+Licheng+Wen%2C+Xuemeng+Yang%2C+Cheng+Yang%2C+Rong+Wu%2C+Tao+Hu%2C+Siqi+Li%2C+Yufan+Shen%2C+Xinyu+Cai%2C+Pinlong+Cai%2C+Botian+Shi%2C+Yong+Liu%2C+and+Yu+Qiao%2E+2025%2E+Re%2Dsearcher%3A+Robust+agentic+sea)
7. Guanzhong He, Zhen Yang, Jinxin Liu, Bin Xu, Lei Hou, and Juanzi Li. 2025. Webseer: Training deeper search agents through reinforcement learning with self-reflection. [find](https://scholar.google.com/scholar?q=Guanzhong+He%2C+Zhen+Yang%2C+Jinxin+Liu%2C+Bin+Xu%2C+Lei+Hou%2C+and+Juanzi+Li%2E+2025%2E+Webseer%3A+Training+deeper+search+agents+through+reinforcement+learning+with+self%2Dreflection%2E)
8. 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/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Comm…
9. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025a. [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/).
10. Jiajie Jin, Yutao Zhu, Zhicheng Dou, Guanting Dong, Xinyu Yang, Chenghao Zhang, Tong Zhao, Zhao Yang, and Ji-Rong Wen. 2025b. [Flashrag: A modular toolkit for efficient retrieval-augmented generation research](https://md.research.elamur.ai/free/en/papers/jin-2024-flashrag-modular-toolkit-efficient-retrieval/). In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 737–740, New York…
11. Mandar Joshi, Eunsol Choi, Daniel 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/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver…
12. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/).
13. 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/)
14. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
15. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Proc…
16. Weizhen Li, Jianbo Lin, Zhuosong Jiang, Jingyi Cao, Xinpeng Liu, Jiayu Zhang, Zhenqiang Huang, Qianben Chen, Weichen Sun, Qiexiang Wang, Hongxuan Lu, Tianrui Qin, Chenghao Zhu, Yi Yao, Shuying Fan, Xiaowan Li, Tiannan Wang, Pai Liu, King Zhu, and 11 others. 2025a. Chain-of-agents: End-to-end agent f… [find](https://scholar.google.com/scholar?q=Weizhen+Li%2C+Jianbo+Lin%2C+Zhuosong+Jiang%2C+Jingyi+Cao%2C+Xinpeng+Liu%2C+Jiayu+Zhang%2C+Zhenqiang+Huang%2C+Qianben+Chen%2C+Weichen+Sun%2C+Qiexiang+Wang%2C+Hongxuan+Lu%2C+Tianrui+Qin%2C+Chenghao+Zhu%2C+Yi+Yao%2C+Shuying+Fan%2C+Xi)
17. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025b. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/).
18. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yongkang Wu, Ji-Rong Wen, Yutao Zhu, and Zhicheng Dou. 2025c. [Webthinker: Empowering large reasoning models with deep research capability](https://md.research.elamur.ai/free/en/papers/li-2025-webthinker-empowering-large-reasoning-models/).
19. 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. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… [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)
20. Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. [find](https://scholar.google.com/scholar?q=Yang%2C+Jiaxi+Yang%2C+Jingren+Zhou%2C+and+25+others%2E+2025%2E+Qwen2%2E5+technical+report%2E)
21. 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: 2409.19256.
22. 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/).
23. 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](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+Transactions+of+the+Association+for+Computational+Li)
24. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2024. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/).
25. Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, and Manling Li. 2025. [Ragen: Understanding self-evolution in llm agents via mult…](https://md.research.elamur.ai/free/en/papers/wang-2025-ragen-understanding-self-evolution-llm/)
26. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837. Curran Associates, Inc.
27. Ting Wu, Xuefeng Li, and Pengfei Liu. 2025. [Progress or regress? self-improvement reversal in post-training](https://md.research.elamur.ai/free/en/papers/wu-2024-progress-regress-self-improvement-reversal/). In The Thirteenth International Conference on Learning Representations.
28. Wenda Xu, Guanglei Zhu, Xuandong Zhao, Liangming Pan, Lei Li, and William Wang. 2024. [Pride and prejudice: LLM amplifies self-bias in self-refinement](https://md.research.elamur.ai/free/en/papers/xu-2024-pride-prejudice-llm-amplifies-self/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15474–15492, Bangkok, Thail…
29. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah 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, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computation)
30. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/).
31. 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 Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Man… — [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/)
32. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–2380, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+2369%E2%80%932380%2C+Brussels%2C+Belgium%2E+Association+for+Computational+Linguistics%2E)
33. A.3 Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, and 16 others. 2025. [Dapo: An open-source llm reinforcement learni…](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/)
34. Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang, Ke Xu, Hewu Li, Liu Yan, and Han Qiu. 2025. [Understanding the dark side of LLMs’ intrinsic self-correction](https://md.research.elamur.ai/free/en/papers/zhang-2025-understanding-dark-side-llms-intrinsic/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)…
35. Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. 2025. [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/).

*Updated 2 November 2026*