Elamur Research⌕
☰
home / papers / 2026 / Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Paper · 2026 · Qianli Ma, Chang Guo, Zhiheng Tian et al.

Summary

The paper addresses AI help for authors writing rebuttals during peer review. Existing tools either fine-tune models on paper–response pairs, which tends to invent experimental results, or rely on long, opaque chat sessions with proprietary LLMs. The authors treat the task as organizing decisions and evidence rather than free-form generation. Their system, RebuttalAgent, is a multi-agent pipeline built around a "verify-then-write" workflow. It splits reviews into atomic concerns and builds a context for each concern that mixes a compressed paper summary with exact manuscript passages. When needed, it searches external literature and turns it into citation-ready briefs. It then drafts a response plan, which a checker audits for consistency and safe commitments, and authors can review it at optional human-in-the-loop checkpoints before the final draft is written. On RebuttalBench, a new benchmark built from ICLR 2023 forums, the pipeline beats direct-to-text and chat-LLM baselines on coverage, faithfulness/traceability and strategic coherence. This matters because rebuttals become auditable and remain under the author's control.

Key points

  • The paper defines four requirements for rebuttal assistance: comprehensive coverage of concerns, strict faithfulness to the manuscript, verifiable grounding of claims, and global consistency across responses.
  • The pipeline has three stages, each run by named agents:
    • Input structuring: Parser, Compressor and concern Extractor, with fidelity and coverage checks.
    • Evidence construction: Search Planner, Retriever, Selector and Analyzer, combining internal and external evidence.
    • Planning and drafting: Response Strategist, Plan Checker and Response Drafter.
  • When a concern calls for new experiments, the system does not produce results. Instead, it outputs scoped to-do lists, marked as MUST or OPTIONAL, which the authors carry out themselves.
  • RebuttalBench is drawn from public ICLR 2023 review forums. Systems are scored with an author-centric rubric covering relevance, coherence and argumentation quality. Specific scores fall in a part of the paper not included in the provided text.
  • A Hugging Face demo and a project page (Paper2Rebuttal.github.io) are available. The authors list latency and cost, limited reuse of artifacts, and differing venue conventions as limitations.

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

🎓Shanghai Jiao Tong UniversityShanghai · China149 works · 16,161 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksHistory and Philosophy of Science · 53 works

Cite

Cite as Qianli Ma, Chang Guo, Zhiheng Tian, Siyu Wang, Jipeng Xiao, Yuanhao Yue and Zhipeng Zhang. 2026. Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance. 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. DOI 10.18653/v1/2026.acl-long.2140

@inproceedings{ma2026paper2rebuttal,
  title = {{Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance}},
  author = {Qianli Ma, Chang Guo, Zhiheng Tian, Siyu Wang, Jipeng Xiao, Yuanhao Yue and Zhipeng 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.2140},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2140}
}

References

45 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gemini Deep Research - your personal research assistant — gemini.google. https://gemini.google/overview/deep-research. [Accessed 22-04-2025]. ↗
  2. Grok 4 \| xAI — x.ai. https://x.ai/news/grok-4. [Accessed 15-10-2025]. ↗
  3. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. 2024. Researchagent: Iterative research idea generation over scientific literature with large language models. arXiv preprint arXiv:2404.07738.
  4. Liying Cheng, Lidong Bing, Qian Yu, Wei Lu, and Luo Si. 2020. Ape: Argument pair extraction from peer review and rebuttal via multi-task learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7000–7011. find
  5. Mike D’Arcy, Tom Hope, Larry Birnbaum, and Doug Downey. 2024. Marg: Multi-agent review generation for scientific papers. arXiv preprint arXiv:2401.04259. find
  6. Bingjie Gao, Qianli Ma, Xiaoxue Wu, Shuai Yang, Guanzhou Lan, Haonan Zhao, Jiaxuan Chen, Qingyang Liu, Yu Qiao, Xinyuan Chen, and 1 others. 2025. Rapo++: Cross-stage prompt optimization for text-to-video generation via data alignment and test-time scaling. arXiv preprint arXiv:2510.20206. — [arXiv:2510.20206](https://arxiv.org/abs/2510.20206) find
  7. Yang Gao, Steffen Eger, Ilia Kuznetsov, Iryna Gurevych, and Yusuke Miyao. 2019. Does my rebuttal matter? insights from a major nlp conference. arXiv preprint arXiv:1903.11367. find
  8. Zhaolin Gao, Kianté Brantley, and Thorsten Joachims. 2024. Reviewer2: Optimizing review generation through prompt generation. arXiv preprint arXiv:2402.10886.
  9. Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, and 1 others. 2025. Pasa: An llm agent for comprehensive academic paper search. arXiv preprint arXiv:2501.10120.
  10. Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, and Zhenzhong Lan. 2024. Nova: An iterative planning and search approach to enhance novelty and diversity of llm generated ideas. arXiv preprint arXiv:2410.14255. find
  11. Ziqi Huang, Fan Zhang, Xiaojie Xu, Yinan He, Jiashuo Yu, Ziyue Dong, Qianli Ma, Nattapol Chanpaisit, Chenyang Si, Yuming Jiang, Yaohui Wang, Xinyuan Chen, Ying-Cong Chen, Limin Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. 2025. VBench++: Comprehensive and versatile benchmark suite for video generative m… find
  12. Yiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen, Kaijie Zhu, Yijia Xiao, and Jindong Wang. 2024. Agentreview: Exploring peer review dynamics with llm agents. In EMNLP. find
  13. M. G. Kendall. 1938. A new measure of rank correlation. Biometrika, 30:81–93. find
  14. Neha Kennard, Tim O’Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, and Andrew McCallum. 2021. Disapere: A dataset for discourse structure in peer review discussions. arXiv preprint arXiv:2110.08520. find
  15. Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu, Zhenning Yang, Yibo Huang, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, and Ang Chen. 2025. Curie: Toward rigorous and automated scientific experimentation with ai agents. arXiv preprint arXiv:2502.16069. find
  16. Guanzhou Lan, Qianli Ma, Yuqi Yang, Zhigang Wang, Dong Wang, Xuelong Li, and Bin Zhao. 2025. Efficient diffusion as low light enhancer. In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pages 21277–21286. find
  17. Yen-Ting Lin and Yun-Nung Chen. 2023. Llm-eval: Unified multi-dimensional automatic evaluation for open-domain conversations with large language models. arXiv preprint arXiv:2305.13711.
  18. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, and 1 others. 2025a. Deepseek-v3. 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
  19. Haokun Liu, Yangqiaoyu Zhou, Mingxuan Li, Chenfei Yuan, and Chenhao Tan. 2024. Literature meets data: A synergistic approach to hypothesis generation. arXiv preprint arXiv:2410.17309.
  20. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, and 3 others. 2025b. Agentbench: Evaluating llms as agents. Preprint, arXiv…
  21. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. 2024. The AI Scientist: Towards fully automated open-ended scientific discovery. arXiv preprint arXiv:2408.06292.
  22. Kai Lu, Shixiong Xu, Jinqiu Li, Kun Ding, and Gaofeng Meng. Agent reviewers: Domain-specific multimodal agents with shared memory for paper review. In Forty-second International Conference on Machine Learning. find
  23. Qianli Ma, Dongrui Liu, Qian Chen, Linfeng Zhang, and Jing Shao. 2025a. Led-merging: Mitigating safety-utility conflicts in model merging with location-election-disjoint. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 21749–…
  24. Qianli Ma, Xuefei Ning, Dongrui Liu, Li Niu, and Linfeng Zhang. 2025b. Decouple-then-merge: Finetune diffusion models as multi-task learning. In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pages 23281–23291. find
  25. Qianli Ma, Siyu Wang, Yilin Chen, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, and Zhipeng Zhang. 2025c. Human-agent collaborative paper-to-page crafting for under $0.1. Preprint, arXiv:2510.19600. find
  26. Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023. Gaia: a benchmark for general ai assistants. Preprint, arXiv:2311.12983.
  27. OpenAI. 2025. Gpt-5 system card. Technical report. Available at: https://cdn.openai.com/gpt-5-system-card.pdf. ↗
  28. Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. 2023. Gorilla: Large language model connected with massive apis. Preprint, arXiv:2305.15334.
  29. Sukannya Purkayastha, Anne Lauscher, and Iryna Gurevych. 2023. Exploring jiu-jitsu argumentation for writing peer review rebuttals. arXiv preprint arXiv:2311.03998. find
  30. Henrik Voigt, Kai Lawonn, and Sina Zarrieß. 2024. Plots made quickly: An efficient approach for generating visualizations from natural language queries. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages… find
  31. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024a. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6).
  32. Yidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu, Meishan Zhang, Xinyu Dai, Qingsong Wen, Wei Ye, and 1 others. 2024b. Autosurvey: Large language models can automatically write surveys. Advances in Neural Information Processing Systems, 37:115119–115145. find
  33. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
  34. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation. Preprint, arXiv:2308.08155.
  35. Chandan K Reddy and Parshin Shojaee. 2025. Towards scientific discovery with generative ai: Progress, opportunities, and challenges. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 28601–28609. find
  36. Yang Wu, Yao Wan, Hongyu Zhang, Yulei Sui, Wucai Wei, Wei Zhao, Guandong Xu, and Hai Jin. 2024. Automated data visualization from natural language via large language models: An exploratory study. Proceedings of the ACM on Management of Data, 2(3):1–28. find
  37. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Preprint, arXiv:2302.04761.
  38. Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David Ha. 2025. The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search. arXiv preprint arXiv:2504.08066.
  39. Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Preprint, arXiv:2303.11366.
  40. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023a. Tree of thoughts: Deliberate problem solving with large language models. Preprint, arXiv:2305.10601. find
  41. Jamshid Sourati and James A Evans. 2023. Accelerating science with human-aware artificial intelligence. Nature human behaviour, 7(10):1682–1696. find
  42. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
  43. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023b. React: Synergizing reasoning and acting in language models. Preprint, arXiv:2210.03629.
  44. Haofei Yu, Zhaochen Hong, Zirui Cheng, Kunlun Zhu, Keyang Xuan, Jinwei Yao, Tao Feng, and Jiaxuan You. 2025. Researchtown: Simulator of human research community. Preprint, arXiv:2412.17767. review volumes to ensure diverse coverage of both positive and negative review samples across tiers.
  45. Daoze Zhang, Zhijian Bao, Sihang Du, Zhiyi Zhao, Kuangling Zhang, Dezheng Bao, and Yang Yang. 2025. Re 2 : A consistency-ensured dataset for full-stage peer review and multi-turn rebuttal discussions. arXiv preprint arXiv:2505.07920. — [arXiv:2505.07920](https://arxiv.org/abs/2505.07920) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ma-2026-paper2rebuttal-multi-agent-framework-transparent/