---
title: "RCBSF — paper by Xu et al. (2026) — summary and ideas"
description: "The authors propose RCBSF (Risk-Constrained Bilevel Stackelberg Framework), which treats… 54 references, cited by 11 papers here."
authors: ["Shijia Xu", "Yu Wang", "Xiaolong Jia", "Zhou Wu", "Kai Liu", "April Xiaowen Dong"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.935/"
doi: "10.18653/v1/2026.findings-acl.935"
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-rcbsf-multi-agent-framework-automated/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-rcbsf-multi-agent-framework-automated/)

[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/) / RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game

# RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game

**Authors:** [Shijia Xu](https://md.research.elamur.ai/free/en/authors/shijia-xu/), [Yu Wang](https://md.research.elamur.ai/free/en/authors/yu-wang/), [Xiaolong Jia](https://md.research.elamur.ai/free/en/authors/xiaolong-jia/), [Zhou Wu](https://md.research.elamur.ai/free/en/authors/zhou-wu/), [Kai Liu](https://md.research.elamur.ai/free/en/authors/kai-liu/) and [April Xiaowen Dong](https://md.research.elamur.ai/free/en/authors/april-xiaowen-dong/) · **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.935/) · [PDF](https://aclanthology.org/2026.findings-acl.935.pdf) · [DOI 10.18653/v1/2026.findings-acl.935](https://doi.org/10.18653/v1/2026.findings-acl.935) · [OpenAlex](https://openalex.org/W7166834728)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [11](https://md.research.elamur.ai/free/en/papers/xu-2026-rcbsf-multi-agent-framework-automated/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses automated contract revision, where general-purpose LLMs often ignore binding legal requirements, invent clauses, or claim fixes they never make. The authors propose RCBSF (Risk-Constrained Bilevel Stackelberg Framework), which treats revision as a hierarchical game rather than a free-form dialogue. A leader agent, the Global Prescriptive Agent (GPA), finds risks using a five-field scheme (Category, Location, Evidence, Issue, Suggestion) and commits first to a prioritized risk budget. A follower pair then works inside those limits over several rounds: the Constrained Revision Agent (CRA) rewrites the text and the Local Verification Agent (LVA) checks it. The authors give a theoretical argument that this bilevel setup reaches an equilibrium with higher utility than unguided prompting. For evaluation, they build a unified benchmark from MAUD, CUAD, ContractNLI and PrivacyQA. Compared with Standard, CoT, RAG and iterative approaches, RCBSF attains a higher Risk Resolution Rate (RRR) while also using tokens more efficiently. Notably, it runs on a small 7B backbone yet outperforms much larger models. This suggests that structured constraints, not model scale, are the more effective route to safer legal text generation.

## Key points
- RCBSF on Qwen2.5-7B reaches 84.21% RRR (GPT-5 judge), compared with 79.56% for iterative refinement and 70.81% for standard prompting. With a 72B backbone, the iterative baseline reaches only 82.60%.
- With larger backbones, RCBSF achieves 85.90% RRR on Llama-3.1-70B and 86.45% on Qwen2.5-72B, with Contract Quality up to 89.10.
- A licensed corporate attorney's blind audit agreed with the GPT-5 judge at Cohen's κ = 0.81. Re-scoring with Claude 3.5 Sonnet, Llama-3.1-70B and Qwen2.5-72B as judges kept the method ranking unchanged, with gains of +3.32 to +6.50 points over the iterative baseline.
- The best settings were 3 game rounds (K = 3) and a GPA softmax temperature of τ = 1.0. More rounds increased token cost with little added RRR.
- Code is released at github.com/xjiacs/RCBSF (Findings of ACL 2026).

*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

- [Queen Mary University of London](https://md.research.elamur.ai/free/en/universities/queen-mary-university-of-london/) — University, London, United Kingdom · 54 works · 3,542 citations
- [Chongqing University](https://md.research.elamur.ai/free/en/universities/chongqing-university/) — University, Chongqing, China · 7 works · 318 citations

📚 Shelves (6): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 182 works

## Cite

Cite as: Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu and April Xiaowen Dong. 2026. RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game. 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{xu2026rcbsf,
  title = {{RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game}},
  author = {Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu and April Xiaowen Dong},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.935},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.935}
}
```

- [← previous Optimizing Length Compression in Large Reasoning Models](https://md.research.elamur.ai/free/en/papers/cheng-2026-optimizing-length-compression-large-reasoning/)
- [next → SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures](https://md.research.elamur.ai/free/en/papers/ousidhoum-2026-semeval-2026-task-7-everyday/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/)

## References

54 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. João Paulo Aires, Roger Granada, Juarez Monteiro, Rodrigo Coelho Barros, and Felipe Meneguzzi. 2019. Classification of contractual conflicts via learning of semantic representations. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’19, page 1764… [find](https://scholar.google.com/scholar?q=Jo%C3%A3o+Paulo+Aires%2C+Roger+Granada%2C+Juarez+Monteiro%2C+Rodrigo+Coelho+Barros%2C+and+Felipe+Meneguzzi%2E+2019%2E+Classification+of+contractual+conflicts+via+learning+of+semantic+representations%2E+In+Proceedings+of)
2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. [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/). Preprint, arXiv:2310.11511.
3. Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Katz, and Nikolaos Aletras. 2022. [LexGLUE: A benchmark dataset for legal language understanding in English](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-lexglue-benchmark-dataset-legal-language/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1:…
4. Huangwei Chen, Wu Li, Junhao Jia, Yining Chen, Xiaotao Pang, Ya-Long Chen, Li Gonghui, Haishuai Wang, Jiajun Bu, and Lei Wu. 2026. Beyond the individual: Virtualizing multi-disciplinary reasoning for clinical intake via collaborative agents. Preprint, arXiv:2604.08927. [find](https://scholar.google.com/scholar?q=Huangwei+Chen%2C+Wu+Li%2C+Junhao+Jia%2C+Yining+Chen%2C+Xiaotao+Pang%2C+Ya%2DLong+Chen%2C+Li+Gonghui%2C+Haishuai+Wang%2C+Jiajun+Bu%2C+and+Lei+Wu%2E+2026%2E+Beyond+the+individual%3A+Virtualizing+multi%2Ddisciplinary+reasoning+for+)
5. World Commerce and Contracting. 2022. A framework for anticipating and managing uncertainty, risk and disruption through enhanced contracting. [find](https://scholar.google.com/scholar?q=World+Commerce+and+Contracting%2E+2022%2E+A+framework+for+anticipating+and+managing+uncertainty%2C+risk+and+disruption+through+enhanced+contracting%2E)
6. Jiaxi Cui, Munan Ning, Zongjian Li, Bohua Chen, Yang Yan, Hao Li, Bin Ling, Yonghong Tian, and Li Yuan. 2024. [Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model](https://md.research.elamur.ai/free/en/papers/cui-2023-chatlaw-multi-agent-legal-assistant/). Preprint, arXiv:2306.16092.
7. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2024. [Improving factuality and reasoning in language models through multiagent debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/). In Forty-first International Conference on Machine Learning.
8. Gabriele Farina, Andrea Celli, Alberto Marchesi, and Nicola Gatti. 2022. Simple uncoupled no-regret learning dynamics for extensive-form correlated equilibrium. J. ACM, 69(6). [find](https://scholar.google.com/scholar?q=Gabriele+Farina%2C+Andrea+Celli%2C+Alberto+Marchesi%2C+and+Nicola+Gatti%2E+2022%2E+Simple+uncoupled+no%2Dregret+learning+dynamics+for+extensive%2Dform+correlated+equilibrium%2E+J%2E+ACM%2C+69%286%29%2E)
9. Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, and Jidong Ge. 2024. [LawBench: Benchmarking legal knowledge of large language models](https://md.research.elamur.ai/free/en/papers/fei-2023-lawbench-benchmarking-legal-knowledge-large/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7933–7962, Miami,…
10. Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Angel Tena, Rémi Kazmierczak, Séverine Dubuisson, Emanuel Aldea, and David Filliat. 2022. Muad: Multiple uncertainties for autonomous driving, a benchmark for multiple uncertainty types and tasks. Preprint, arXiv:2203.01437. — [arXiv:2203.01437](https://arxiv.org/abs/2203.01437) [find](https://scholar.google.com/scholar?q=Gianni+Franchi%2C+Xuanlong+Yu%2C+Andrei+Bursuc%2C+Angel+Tena%2C+R%C3%A9mi+Kazmierczak%2C+S%C3%A9verine+Dubuisson%2C+Emanuel+Aldea%2C+and+David+Filliat%2E+2022%2E+Muad%3A+Multiple+uncertainties+for+autonomous+driving%2C+a+benchmark+f)
11. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997.
12. Xueren Ge, Sahil Murtaza, Anthony Cortez, and Homa Alemzadeh. 2026. Emsdialog: Synthetic multi-person emergency medical service dialogue generation from electronic patient care reports via multi-llm agents. Preprint, arXiv:2604.07549. [find](https://scholar.google.com/scholar?q=Xueren+Ge%2C+Sahil+Murtaza%2C+Anthony+Cortez%2C+and+Homa+Alemzadeh%2E+2026%2E+Emsdialog%3A+Synthetic+multi%2Dperson+emergency+medical+service+dialogue+generation+from+electronic+patient+care+reports+via+multi%2Dllm+a)
13. Neel Guha, Julian Nyarko, Daniel Ho, Christopher Ré, Adam Chilton, Aditya K, Alex Chohlas-Wood, Austin Peters, Brandon Waldon, Daniel Rockmore, Diego Zambrano, Dmitry Talisman, Enam Hoque, Faiz Surani, Frank Fagan, Galit Sarfaty, Gregory Dickinson, Haggai Porat, Jason Hegland, and 21 others. 2023. L… — [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/guha-2023-legalbench-collaboratively-built-benchmark-measuring/)
14. Dan Hendrycks, Collin Burns, Anya Chen, and Spencer Ball. 2021. [Cuad: An expert-annotated nlp dataset for legal contract review](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-cuad-expert-annotated-nlp-dataset/). Preprint, arXiv:2103.06268.
15. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. [MetaGPT: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In The T…
16. Yu-Guan Hsieh, Kimon Antonakopoulos, Volkan Cevher, and Panayotis Mertikopoulos. 2022. No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation. In Advances in Neural Information Processing Systems, volume 35, pages 6544–6556. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Yu%2DGuan+Hsieh%2C+Kimon+Antonakopoulos%2C+Volkan+Cevher%2C+and+Panayotis+Mertikopoulos%2E+2022%2E+No%2Dregret+learning+in+games+with+noisy+feedback%3A+Faster+rates+and+adaptivity+via+learning+rate+separation%2E+In+Adv)
17. Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, and Zhi Wang. 2026. Semantic-space exploration and exploitation in rlvr for llm reasoning. Preprint, arXiv:2509.23808. [find](https://scholar.google.com/scholar?q=Fanding+Huang%2C+Guanbo+Huang%2C+Xiao+Fan%2C+Yi+He%2C+Xiao+Liang%2C+Xiao+Chen%2C+Qinting+Jiang%2C+Faisal+Nadeem+Khan%2C+Jingyan+Jiang%2C+and+Zhi+Wang%2E+2026%2E+Semantic%2Dspace+exploration+and+exploitation+in+rlvr+for+llm+r)
18. Quzhe Huang, Mingxu Tao, Chen Zhang, Zhenwei An, Cong Jiang, Zhibin Chen, Zirui Wu, and Yansong Feng. 2023. [Lawyer llama technical report](https://md.research.elamur.ai/free/en/papers/huang-2023-lawyer-llama-technical-report/). Preprint, arXiv:2305.15062.
19. Zhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang, Yingli Zhou, Di Jiang, Zeying Xie, and Xiaofang Zhou. 2025. Licomemory: Lightweight and cognitive agentic memory for efficient long-term reasoning. arXiv preprint arXiv:2511.01448. [find](https://scholar.google.com/scholar?q=Zhengjun+Huang%2C+Zhoujin+Tian%2C+Qintian+Guo%2C+Fangyuan+Zhang%2C+Yingli+Zhou%2C+Di+Jiang%2C+Zeying+Xie%2C+and+Xiaofang+Zhou%2E+2025%2E+Licomemory%3A+Lightweight+and+cognitive+agentic+memory+for+efficient+long%2Dterm+reas)
20. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Comput. Surv., 55(12).
21. Cong Jiang and Xiaolei Yang. 2023. Legal syllogism prompting: Teaching large language models for legal judgment prediction. In Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law, ICAIL ’23, page 417–421, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Cong+Jiang+and+Xiaolei+Yang%2E+2023%2E+Legal+syllogism+prompting%3A+Teaching+large+language+models+for+legal+judgment+prediction%2E+In+Proceedings+of+the+Nineteenth+International+Conference+on+Artificial+Inte)
22. Dongming Jiang, Yi Li, Guanpeng Li, and Bingzhe Li. 2026a. [Magma: A multi-graph based agentic memory architecture for ai agents](https://md.research.elamur.ai/free/en/papers/jiang-2026-magma-multi-graph-based-agentic/). Preprint, arXiv:2601.03236.
23. Dongming Jiang, Yi Li, Songtao Wei, Jinxin Yang, Ayushi Kishore, Alysa Zhao, Dingyi Kang, Xu Hu, Feng Chen, Qiannan Li, and Bingzhe Li. 2026b. Anatomy of agentic memory: Taxonomy and empirical analysis of evaluation and system limitations. Preprint, arXiv:2602.19320. — [arXiv:2602.19320](https://arxiv.org/abs/2602.19320) [find](https://scholar.google.com/scholar?q=Dongming+Jiang%2C+Yi+Li%2C+Songtao+Wei%2C+Jinxin+Yang%2C+Ayushi+Kishore%2C+Alysa+Zhao%2C+Dingyi+Kang%2C+Xu+Hu%2C+Feng+Chen%2C+Qiannan+Li%2C+and+Bingzhe+Li%2E+2026b%2E+Anatomy+of+agentic+memory%3A+Taxonomy+and+empirical+analysi)
24. Zhaolu Kang, Junhao Gong, Qingxi Chen, Hao Zhang, Jiaxin Liu, Rong Fu, Zhiyuan Feng, Yuan Wang, Simon Fong, and Kaiyue Zhou. 2026. Multimodal multi-agent empowered legal judgment prediction. Preprint, arXiv:2601.12815. [find](https://scholar.google.com/scholar?q=Zhaolu+Kang%2C+Junhao+Gong%2C+Qingxi+Chen%2C+Hao+Zhang%2C+Jiaxin+Liu%2C+Rong+Fu%2C+Zhiyuan+Feng%2C+Yuan+Wang%2C+Simon+Fong%2C+and+Kaiyue+Zhou%2E+2026%2E+Multimodal+multi%2Dagent+empowered+legal+judgment+prediction%2E+Preprint%2C)
25. Daniel Martin Katz, Michael James Bommarito, Shang Gao, and Pablo Arredondo. 2024. Gpt-4 passes the bar exam. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 382(2270):20230254. [find](https://scholar.google.com/scholar?q=Daniel+Martin+Katz%2C+Michael+James+Bommarito%2C+Shang+Gao%2C+and+Pablo+Arredondo%2E+2024%2E+Gpt%2D4+passes+the+bar+exam%2E+Philosophical+Transactions+of+the+Royal+Society+A%3A+Mathematical%2C+Physical+and+Engineering+)
26. Yuta Koreeda and Christopher Manning. 2021. [ContractNLI: A dataset for document-level natural language inference for contracts](https://md.research.elamur.ai/free/en/papers/koreeda-2021-contractnli-dataset-document-level-natural/). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1907–1919, Punta Cana, Dominican Republic. Association for Computational Linguistics.
27. Jinqi Lai, Wensheng Gan, Jiayang Wu, Zhenlian Qi, and Philip S. Yu. 2024. Large language models in law: A survey. AI Open, 5:181–196. [find](https://scholar.google.com/scholar?q=Jinqi+Lai%2C+Wensheng+Gan%2C+Jiayang+Wu%2C+Zhenlian+Qi%2C+and+Philip+S%2E+Yu%2E+2024%2E+Large+language+models+in+law%3A+A+survey%2E+AI+Open%2C+5%3A181%E2%80%93196%2E)
28. 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…
29. Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, and Wei Ye. 2026a. [Retrieval as generation: A unified framework with self-triggered information planning](https://md.research.elamur.ai/free/en/papers/li-2026-retrieval-as-generation-unified-framework/). Preprint, arXiv:2604.11407.
30. Guocong Li, Jinjian Zhang, Ping Wang, Dongnan Liu, Tian Liang, Qiuyi Qi, Hao Huang, Siyan Guo, Mutian Bao, Wei Zhou, Linjian Mo, Hongxia Xu, and Jian Wu. 2026b. Mol: Adaptive mixture-of-length reasoning for efficient question answering with context. In The Fourteenth International Conference on Lear… [find](https://scholar.google.com/scholar?q=Guocong+Li%2C+Jinjian+Zhang%2C+Ping+Wang%2C+Dongnan+Liu%2C+Tian+Liang%2C+Qiuyi+Qi%2C+Hao+Huang%2C+Siyan+Guo%2C+Mutian+Bao%2C+Wei+Zhou%2C+Linjian+Mo%2C+Hongxia+Xu%2C+and+Jian+Wu%2E+2026b%2E+Mol%3A+Adaptive+mixture%2Dof%2Dlength+reasoni)
31. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [Camel: Communicative agents for "mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). In Advances in Neural Information Processing Systems, volume 36, pages 51991–52008. Curran Associates, Inc.
32. Yuxi Sun, Aoqi Zuo, Wei Gao, and Jing Ma. 2025. Causalabstain: Enhancing multilingual llms with causal reasoning for trustworthy abstention. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14060–14076. [find](https://scholar.google.com/scholar?q=Yuxi+Sun%2C+Aoqi+Zuo%2C+Wei+Gao%2C+and+Jing+Ma%2E+2025%2E+Causalabstain%3A+Enhancing+multilingual+llms+with+causal+reasoning+for+trustworthy+abstention%2E+In+Findings+of+the+Association+for+Computational+Linguistic)
33. Hongye Liu and Ricardo Henao. 2025. Learning to substitute words with model-based score ranking. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 11551–11565. [find](https://scholar.google.com/scholar?q=Hongye+Liu+and+Ricardo+Henao%2E+2025%2E+Learning+to+substitute+words+with+model%2Dbased+score+ranking%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas+Chapter+of+the+Association+for+Com)
34. Tailong Luo, Hao Li, Rong Fu, Xinyue Jiang, Huaxuan Ding, Yiduo Zhang, Zilin Zhao, Simon Fong, Guangyin Jin, and Jianyuan Ni. 2026. Multipress: A multi-agent framework for interpretable multimodal news classification. Preprint, arXiv:2604.03586. — [arXiv:2604.03586](https://arxiv.org/abs/2604.03586) [find](https://scholar.google.com/scholar?q=Tailong+Luo%2C+Hao+Li%2C+Rong+Fu%2C+Xinyue+Jiang%2C+Huaxuan+Ding%2C+Yiduo+Zhang%2C+Zilin+Zhao%2C+Simon+Fong%2C+Guangyin+Jin%2C+and+Jianyuan+Ni%2E+2026%2E+Multipress%3A+A+multi%2Dagent+framework+for+interpretable+multimodal+new)
35. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with… [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+Shashank+Gupta%2C+Bodhisattwa+Prasad+Majumder%2C+Katherine+Her)
36. John J. Nay, David Karamardian, Sarah B. Lawsky, Wenting Tao, Meghana Bhat, Raghav Jain, Aaron Travis Lee, Jonathan H. Choi, and Jungo Kasai. 2024. [Large language models as tax attorneys: a case study in legal capabilities emergence](https://md.research.elamur.ai/free/en/papers/nay-2023-large-language-models-tax-attorneys/). Philosophical Transactions of the Royal Society A: Mathematical, P…
37. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/)
38. Abhilasha Ravichander, Alan W Black, Shomir Wilson, Thomas Norton, and Norman Sadeh. 2019. [Question answering for privacy policies: Combining computational and legal perspectives](https://md.research.elamur.ai/free/en/papers/ravichander-2019-question-answering-privacy-policies-combining/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Join…
39. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement Yuxi Sun, Aoqi Zuo, Haotian Xie, Wei Gao, Mingming Gong, and Jing Ma. 2026. [Fact-e: Causality-inspired evaluation for trustworthy chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/sun-2026-fact-e-causality-inspired-evaluation/).… — [arXiv:2604.10693](https://arxiv.org/abs/2604.10693)
40. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazari… — [Gemini: A Family of Highly Capable Multimodal Models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/)
41. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
42. Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2026a. Think-while-generating: On-the-fly reasoning for personalized long-form generation. Preprint, arXiv:2512.06690. — [arXiv:2512.06690](https://arxiv.org/abs/2512.06690) [find](https://scholar.google.com/scholar?q=Chengbing+Wang%2C+Yang+Zhang%2C+Wenjie+Wang%2C+Xiaoyan+Zhao%2C+Fuli+Feng%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2026a%2E+Think%2Dwhile%2Dgenerating%3A+On%2Dthe%2Dfly+reasoning+for+personalized+long%2Dform+generation%2E+Preprint%2C+a)
43. Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, and Fuli Feng. 2026b. [Perm: Psychology-grounded empathetic reward modeling for large language models](https://md.research.elamur.ai/free/en/papers/wang-2026-perm-psychology-grounded-empathetic-reward/). Preprint, arXiv:2601.10532.
44. Steven Wang, Antoine Scardigli, Leonard Tang, Wei Chen, Dmitry Levkin, Anya Chen, Spencer Ball, Thomas Woodside, Oliver Zhang, and Dan Hendrycks. 2023. MAUD: An expert-annotated legal NLP dataset for merger agreement understanding. In Proceedings of the 2023 Conference on Empirical Methods in Natura… [find](https://scholar.google.com/scholar?q=Steven+Wang%2C+Antoine+Scardigli%2C+Leonard+Tang%2C+Wei+Chen%2C+Dmitry+Levkin%2C+Anya+Chen%2C+Spencer+Ball%2C+Thomas+Woodside%2C+Oliver+Zhang%2C+and+Dan+Hendrycks%2E+2023%2E+MAUD%3A+An+expert%2Dannotated+legal+NLP+dataset+for+)
45. Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, and Tomas Pfister. 2025. Speculative rag: Enhancing retrieval augmented generation through drafting. Preprint, arXiv:2407.08223. — [arXiv:2407.08223](https://arxiv.org/abs/2407.08223) [find](https://scholar.google.com/scholar?q=Zilong+Wang%2C+Zifeng+Wang%2C+Long+Le%2C+Huaixiu+Steven+Zheng%2C+Swaroop+Mishra%2C+Vincent+Perot%2C+Yuwei+Zhang%2C+Anush+Mattapalli%2C+Ankur+Taly%2C+Jingbo+Shang%2C+Chen%2DYu+Lee%2C+and+Tomas+Pfister%2E+2025%2E+Speculative+rag%3A+)
46. 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.
47. Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, and Zhen-Hua Ling. 2024. [Corrective retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/yan-2024-corrective-retrieval-augmented-generation/).
48. Tianyu Yang, Yuhan Liu, Sobin Alosious, Ethan A. Brown, Jason R. Rohr, Tengfei Luo, and Xiangliang Zhang. 2025. Quest2dataagent: Automating end-to-end scientific data collection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 5… [find](https://scholar.google.com/scholar?q=Tianyu+Yang%2C+Yuhan+Liu%2C+Sobin+Alosious%2C+Ethan+A%2E+Brown%2C+Jason+R%2E+Rohr%2C+Tengfei+Luo%2C+and+Xiangliang+Zhang%2E+2025%2E+Quest2dataagent%3A+Automating+end%2Dto%2Dend+scientific+data+collection%2E+In+Proceedings+of+the)
49. Xiaoxian Yang, Zhifeng Wang, Qi Wang, Ke Wei, Kaiqi Zhang, and Jiangang Shi. 2024. Large language models for automated q&a involving legal documents: a survey on algorithms, frameworks and applications. International Journal of Web Information Systems, 20(4):413–435. [find](https://scholar.google.com/scholar?q=Xiaoxian+Yang%2C+Zhifeng+Wang%2C+Qi+Wang%2C+Ke+Wei%2C+Kaiqi+Zhang%2C+and+Jiangang+Shi%2E+2024%2E+Large+language+models+for+automated+q%26a+involving+legal+documents%3A+a+survey+on+algorithms%2C+frameworks+and+application)
50. Shengbin Yue, Wei Chen, Siyuan Wang, Bingxuan Li, Chenchen Shen, Shujun Liu, Yuxuan Zhou, Yao Xiao, Song Yun, Xuanjing Huang, and Zhongyu Wei. 2023. Disc-lawllm: Fine-tuning large language models for intelligent legal services. Preprint, arXiv:2309.11325. [find](https://scholar.google.com/scholar?q=Shengbin+Yue%2C+Wei+Chen%2C+Siyuan+Wang%2C+Bingxuan+Li%2C+Chenchen+Shen%2C+Shujun+Liu%2C+Yuxuan+Zhou%2C+Yao+Xiao%2C+Song+Yun%2C+Xuanjing+Huang%2C+and+Zhongyu+Wei%2E+2023%2E+Disc%2Dlawllm%3A+Fine%2Dtuning+large+language+models+for+)
51. Shengbin Yue, Shujun Liu, Yuxuan Zhou, Chenchen Shen, Siyuan Wang, Yao Xiao, Bingxuan Li, Yun Song, Xiaoyu Shen, Wei Chen, Xuanjing Huang, and Zhongyu Wei. 2024. Lawllm: Intelligent legal system with legal reasoning and verifiable retrieval. In Database Systems for Advanced Applications, pages 304–3… [find](https://scholar.google.com/scholar?q=Shengbin+Yue%2C+Shujun+Liu%2C+Yuxuan+Zhou%2C+Chenchen+Shen%2C+Siyuan+Wang%2C+Yao+Xiao%2C+Bingxuan+Li%2C+Yun+Song%2C+Xiaoyu+Shen%2C+Wei+Chen%2C+Xuanjing+Huang%2C+and+Zhongyu+Wei%2E+2024%2E+Lawllm%3A+Intelligent+legal+system+with+)
52. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026. [Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-stable-rag-mitigating-retrieval-permutation/). Preprint, arXiv:2601.02993.
53. Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. 2020. [How does nlp benefit legal system: A summary of legal artificial intelligence](https://md.research.elamur.ai/free/en/papers/zhong-2020-how-does-nlp-benefit-legal/). Preprint, arXiv:2004.12158.
54. Yixi Zhou, Fan Zhang, Yu Chen, Haipeng Zhang, Preslav Nakov, and Zhuohan Xie. 2026. [Fincards: Card-based analyst reranking for financial document question answering](https://md.research.elamur.ai/free/en/papers/zhou-2026-fincards-card-based-analyst-reranking/). Preprint, arXiv:2601.06992.

*Updated 30 October 2026*