---
title: "MERIT Feedback Elicits Better Bargaining in LLM Negotiators"
description: "LLM negotiators often bargain shallowly. 48 references. Among them: 0."
authors: ["Jihwan Oh", "Murad Aghazada", "Yooju Shin", "Se-Young Yun", "Taehyeon Kim"]
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.1155/"
doi: "10.18653/v1/2026.acl-long.1155"
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/oh-2026-merit-feedback-elicits-better-bargaining/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/oh-2026-merit-feedback-elicits-better-bargaining/)

[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/36/) / MERIT Feedback Elicits Better Bargaining in LLM Negotiators

# MERIT Feedback Elicits Better Bargaining in LLM Negotiators

**Authors:** [Jihwan Oh](https://md.research.elamur.ai/free/en/authors/jihwan-oh/), Murad Aghazada, Yooju Shin, [Se-Young Yun](https://md.research.elamur.ai/free/en/authors/se-young-yun/) and [Taehyeon Kim](https://md.research.elamur.ai/free/en/authors/taehyeon-kim/) · **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.1155/) · [PDF](https://aclanthology.org/2026.acl-long.1155.pdf) · [DOI 10.18653/v1/2026.acl-long.1155](https://doi.org/10.18653/v1/2026.acl-long.1155) · [OpenAlex](https://openalex.org/W7166836244)

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

## Summary
LLM negotiators often bargain shallowly. They adapt poorly to opponents and to realistic market complications, and existing bargaining benchmarks are mostly single-issue and judge success by profit alone. The authors address this with three components:

- **AgoraBench**, a buyer–seller simulator with nine economically motivated market regimes, such as deception, monopoly, installment payments, negative seller reputation and multi-product choice.
- **MERIT**, an evaluation grounded in utility theory. It combines monetary gain with whether the buyer actually obtains the product it preferred.
- **A human preference dataset**, built from LLM-vs-LLM dialogues that MTurk workers judged.

MERIT is then used as feedback in two ways: in-context learning (ICL-MF) and LoRA fine-tuning of gpt-oss-20b on human-preferred dialogues. Both raise MERIT scores and deal rates over a ReAct baseline, with the clearest gains in multi-product settings. The MERIT-guided agents also reason more explicitly about the opponent, for example by estimating the seller's hidden cost. The work matters because it shifts evaluation of bargaining agents toward human-aligned outcomes instead of naive price minimisation.

## Key points
- **Simulator design.** AgoraBench builds its nine regimes from five single-product and four multi-product settings. Every non-vanilla market includes a deception layer. Agents follow a Thoughts–Talk–Action (ReAct) format with the actions BUY, SELL, REJECT, DEAL and QUIT.
- **Metric components.** MERIT draws on agent utility, negotiation power and acquisition ratio, covering both cardinal and ordinal aspects of utility.
- **Main results against a DeepSeek-v3.2 seller.** For gpt-oss-20b in multi-product markets:
  - MERIT rose from 0.986 (ReAct) to 1.410 (ICL-MF) and 1.459 (SFT).
  - Deal rate rose from 65.3% to 86.6% and 93.1%.
  - In single-product markets, ICL-MF was best (1.413 MERIT, 91.3% deal rate).
- **Out-of-distribution test.** The SFT model was trained only on the Deceptive regime against GPT and Gemini opponents. It was evaluated on all nine regimes and against an unseen seller.
- **LLM-judge evaluation.** gemma-3-27b-it acted as judge and preferred ICL-MF dialogues:
  - against OG-Narrator, a mean of about 84.7%, with the deceptive market showing the highest share at 94.4%;
  - against ReAct, roughly 70–83%.
- **Release.** Code and data are on GitHub (ericoh929/Agorabench).

*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

- [Korea Advanced Institute of Science and Technology](https://md.research.elamur.ai/free/en/universities/korea-advanced-institute-of-science-and-technology/) — University, Daejeon, South Korea · 51 works · 3,167 citations
- [LG AI Research](https://md.research.elamur.ai/free/en/companies/lg-ai-research/) — Company, Seoul, South Korea · 7 works · 374 citations

📚 Shelves (4): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Jihwan Oh, Murad Aghazada, Yooju Shin, Se-Young Yun and Taehyeon Kim. 2026. MERIT Feedback Elicits Better Bargaining in LLM Negotiators. 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{oh2026merit,
  title = {{MERIT Feedback Elicits Better Bargaining in LLM Negotiators}},
  author = {Jihwan Oh, Murad Aghazada, Yooju Shin, Se-Young Yun and Taehyeon Kim},
  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.1155},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1155}
}
```

- [← previous Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance](https://md.research.elamur.ai/free/en/papers/ueda-2026-merging-continual-pretraining-models-domain/)
- [next → MeSHClass-ES and AnatEM-ES: Open Resources for Spanish Biomedical NLP](https://md.research.elamur.ai/free/en/papers/novoa-2026-meshclass-es-anatem-es-open/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

48 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, and Mario Fritz. 2024. Cooperation, competition, and maliciousness: Llm-stakeholders interactive negotiation. Advances in Neural Information Processing Systems, 37:83548–83599. [find](https://scholar.google.com/scholar?q=Sahar+Abdelnabi%2C+Amr+Gomaa%2C+Sarath+Sivaprasad%2C+Lea+Sch%C3%B6nherr%2C+and+Mario+Fritz%2E+2024%2E+Cooperation%2C+competition%2C+and+maliciousness%3A+Llm%2Dstakeholders+interactive+negotiation%2E+Advances+in+Neural+Informati)
2. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, and 1 others. 2025. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). arXiv preprint arXiv:2508.10925.
3. Anthropic. 2025. Claude sonnet 4.5 system card. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Claude+sonnet+4%2E5+system+card%2E)
4. Linda Babcock and George Loewenstein. 1997. Explaining bargaining impasse: The role of self-serving biases. Journal of Economic perspectives, 11(1):109– 126. [find](https://scholar.google.com/scholar?q=Linda+Babcock+and+George+Loewenstein%2E+1997%2E+Explaining+bargaining+impasse%3A+The+role+of+self%2Dserving+biases%2E+Journal+of+Economic+perspectives%2C+11%281%29%3A109%E2%80%93+126%2E)
5. Matthew Backus, Thomas Blake, Jett Pettus, and Steven Tadelis. 2020. Communication and bargaining breakdown: An empirical analysis. Technical report, National Bureau of Economic Research. [find](https://scholar.google.com/scholar?q=Matthew+Backus%2C+Thomas+Blake%2C+Jett+Pettus%2C+and+Steven+Tadelis%2E+2020%2E+Communication+and+bargaining+breakdown%3A+An+empirical+analysis%2E+Technical+report%2C+National+Bureau+of+Economic+Research%2E)
6. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, and 1 others. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862. [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+and+1+others%2E+2022%2E+Training+a+helpful+and+harmless+assistant+wi)
7. Federico Bianchi, Patrick John Chia, Mert Yuksekgonul, Jacopo Tagliabue, Dan Jurafsky, and James Zou. 2024. How well can llms negotiate? negotiationarena platform and analysis. arXiv preprint arXiv:2402.05863. [find](https://scholar.google.com/scholar?q=Federico+Bianchi%2C+Patrick+John+Chia%2C+Mert+Yuksekgonul%2C+Jacopo+Tagliabue%2C+Dan+Jurafsky%2C+and+James+Zou%2E+2024%2E+How+well+can+llms+negotiate%3F+negotiationarena+platform+and+analysis%2E+arXiv+preprint+arXiv%3A24)
8. Ken Binmore, Ariel Rubinstein, and Asher Wolinsky. 1986. The nash bargaining solution in economic modelling. The RAND Journal of Economics, pages 176–188. [find](https://scholar.google.com/scholar?q=Ken+Binmore%2C+Ariel+Rubinstein%2C+and+Asher+Wolinsky%2E+1986%2E+The+nash+bargaining+solution+in+economic+modelling%2E+The+RAND+Journal+of+Economics%2C+pages+176%E2%80%93188%2E)
9. Ralph Allan Bradley and Milton E. Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324– 345. [find](https://scholar.google.com/scholar?q=Ralph+Allan+Bradley+and+Milton+E%2E+Terry%2E+1952%2E+Rank+analysis+of+incomplete+block+designs%3A+I%2E+the+method+of+paired+comparisons%2E+Biometrika%2C+39%283%2F4%29%3A324%E2%80%93+345%2E)
10. Kalyan Chatterjee and William Samuelson. 1983. Bargaining under incomplete information. Operations research, 31(5):835–851. [find](https://scholar.google.com/scholar?q=Kalyan+Chatterjee+and+William+Samuelson%2E+1983%2E+Bargaining+under+incomplete+information%2E+Operations+research%2C+31%285%29%3A835%E2%80%93851%2E)
11. Siqi Chen and Gerhard Weiss. 2025. Enhancing agent-based negotiation strategies via transfer learning. Electronics, 14(17):3391. [find](https://scholar.google.com/scholar?q=Siqi+Chen+and+Gerhard+Weiss%2E+2025%2E+Enhancing+agent%2Dbased+negotiation+strategies+via+transfer+learning%2E+Electronics%2C+14%2817%29%3A3391%2E)
12. Wei-Lin Chiang, Zhuohan Li, Ziqing Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, and 1 others. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See [https://vicuna.lmsys](https://vicuna.lmsys). org (accessed 14 April 2023), 2(3):6. [↗](https://vicuna.lmsys)
13. Deuksin Kwon, Jiwon Hae, Emma Clift, Daniel Sham-soddini, Jonathan Gratch, and Gale Lucas. 2025. Astra: A negotiation agent with adaptive and strategic reasoning via tool-integrated action for dynamic offer optimization. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language… [find](https://scholar.google.com/scholar?q=Deuksin+Kwon%2C+Jiwon+Hae%2C+Emma+Clift%2C+Daniel+Sham%2Dsoddini%2C+Jonathan+Gratch%2C+and+Gale+Lucas%2E+2025%2E+Astra%3A+A+negotiation+agent+with+adaptive+and+strategic+reasoning+via+tool%2Dintegrated+action+for+dynamic)
14. Younwoo Choi, Changling Li, Yongjin Yang, and Zhijing Jin. 2025. Agent-to-agent theory of mind: Testing interlocutor awareness among large language models. arXiv preprint arXiv:2506.22957. [find](https://scholar.google.com/scholar?q=Younwoo+Choi%2C+Changling+Li%2C+Yongjin+Yang%2C+and+Zhijing+Jin%2E+2025%2E+Agent%2Dto%2Dagent+theory+of+mind%3A+Testing+interlocutor+awareness+among+large+language+models%2E+arXiv+preprint+arXiv%3A2506%2E22957%2E)
15. Deuksin Kwon, Emily Weiss, Tara Kulshrestha, Kushal Chawla, Gale M Lucas, and Jonathan Gratch. 2024. Are llms effective negotiators? systematic evaluation of the multifaceted capabilities of llms in negotiation dialogues. arXiv preprint arXiv:2402.13550. [find](https://scholar.google.com/scholar?q=Deuksin+Kwon%2C+Emily+Weiss%2C+Tara+Kulshrestha%2C+Kushal+Chawla%2C+Gale+M+Lucas%2C+and+Jonathan+Gratch%2E+2024%2E+Are+llms+effective+negotiators%3F+systematic+evaluation+of+the+multifaceted+capabilities+of+llms+in+n)
16. Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Paul+F+Christiano%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+2017%2E+Deep+reinforcement+learning+from+human+preferences%2E+Advances+in+neural+information+processing+systems%2C+30%2E)
17. Yuan Deng, Vahab Mirrokni, Renato Paes Leme, Hanrui Zhang, and Song Zuo. 2024. Llms at the bargaining table. In Agentic Markets Workshop at ICML, volume 2024. [find](https://scholar.google.com/scholar?q=Yuan+Deng%2C+Vahab+Mirrokni%2C+Renato+Paes+Leme%2C+Hanrui+Zhang%2C+and+Song+Zuo%2E+2024%2E+Llms+at+the+bargaining+table%2E+In+Agentic+Markets+Workshop+at+ICML%2C+volume+2024%2E)
18. Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. 2023. [Improving language model negotiation with self-play and in-context learning from ai feedback](https://md.research.elamur.ai/free/en/papers/fu-2023-improving-language-model-negotiation-self/). arXiv preprint arXiv:2305.10142.
19. Google DeepMind. 2025. Gemini 3 flash model card. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2025%2E+Gemini+3+flash+model+card%2E)
20. Zhenyu Guan, Xiangyu Kong, Fangwei Zhong, and Yizhou Wang. 2024. Richelieu: Self-evolving llm-based agents for ai diplomacy. Advances in Neural Information Processing Systems, 37:123471–123497. [find](https://scholar.google.com/scholar?q=Zhenyu+Guan%2C+Xiangyu+Kong%2C+Fangwei+Zhong%2C+and+Yizhou+Wang%2E+2024%2E+Richelieu%3A+Self%2Devolving+llm%2Dbased+agents+for+ai+diplomacy%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A123471%E2%80%93123497%2E)
21. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. [Decoupling strategy and generation in negotiation dialogues](https://md.research.elamur.ai/free/en/papers/he-2018-decoupling-strategy-generation-negotiation-dialogues/). arXiv preprint arXiv:1808.09637.
22. Kaitlyn Henderson. 2024. The crisis of low wages: Who earns less than $17 an hour in the us in 2024? [find](https://scholar.google.com/scholar?q=Kaitlyn+Henderson%2E+2024%2E+The+crisis+of+low+wages%3A+Who+earns+less+than+%2417+an+hour+in+the+us+in+2024%3F)
23. Wenyue Hua, Ollie Liu, Lingyao Li, Alfonso Amayuelas, Julie Chen, Lucas Jiang, Mingyu Jin, Lizhou Fan, Fei Sun, William Wang, and 1 others. 2024. Game-theoretic llm: Agent workflow for negotiation games. arXiv preprint arXiv:2411.05990. — [arXiv:2411.05990](https://arxiv.org/abs/2411.05990) [find](https://scholar.google.com/scholar?q=Wenyue+Hua%2C+Ollie+Liu%2C+Lingyao+Li%2C+Alfonso+Amayuelas%2C+Julie+Chen%2C+Lucas+Jiang%2C+Mingyu+Jin%2C+Lizhou+Fan%2C+Fei+Sun%2C+William+Wang%2C+and+1+others%2E+2024%2E+Game%2Dtheoretic+llm%3A+Agent+workflow+for+negotiation+gam)
24. Ilwoo Hwang. 2018. A theory of bargaining deadlock. Games and Economic Behavior, 109:501–522. [find](https://scholar.google.com/scholar?q=Ilwoo+Hwang%2E+2018%2E+A+theory+of+bargaining+deadlock%2E+Games+and+Economic+Behavior%2C+109%3A501%E2%80%93522%2E)
25. Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Aniruddha Kembhavi, and Kiana Ehsani. 2024. Promptable behaviors: Personalizing multi-objective rewards from human preferences. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16216–16226. [find](https://scholar.google.com/scholar?q=Minyoung+Hwang%2C+Luca+Weihs%2C+Chanwoo+Park%2C+Kimin+Lee%2C+Aniruddha+Kembhavi%2C+and+Kiana+Ehsani%2E+2024%2E+Promptable+behaviors%3A+Personalizing+multi%2Dobjective+rewards+from+human+preferences%2E+In+Proceedings+of+t)
26. Geoffrey A Jehle. 2011. Advanced Microeconomic Theory 3rd ed. Prentice-Hall, Inc. [find](https://scholar.google.com/scholar?q=Geoffrey+A+Jehle%2E+2011%2E+Advanced+Microeconomic+Theory+3rd+ed%2E+Prentice%2DHall%2C+Inc%2E)
27. W Bradley Knox, Stephane Hatgis-Kessell, Serena Booth, Scott Niekum, Peter Stone, and Alessandro Allievi. 2022. Models of human preference for learning reward functions. arXiv preprint arXiv:2206.02231. — [arXiv:2206.02231](https://arxiv.org/abs/2206.02231) [find](https://scholar.google.com/scholar?q=W+Bradley+Knox%2C+Stephane+Hatgis%2DKessell%2C+Serena+Booth%2C+Scott+Niekum%2C+Peter+Stone%2C+and+Alessandro+Allievi%2E+2022%2E+Models+of+human+preference+for+learning+reward+functions%2E+arXiv+preprint+arXiv%3A2206%2E0223)
28. Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, and Jennifer Neville. 2025. [Llms get lost in multi-turn conversation](https://md.research.elamur.ai/free/en/papers/laban-2025-llms-get-lost-multi-turn/). arXiv preprint arXiv:2505.06120.
29. Mike Lewis, Denis Yarats, Yann N Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or no deal? end-to-end learning for negotiation dialogues. arXiv preprint arXiv:1706.05125. — [arXiv:1706.05125](https://arxiv.org/abs/1706.05125) [find](https://scholar.google.com/scholar?q=Mike+Lewis%2C+Denis+Yarats%2C+Yann+N+Dauphin%2C+Devi+Parikh%2C+and+Dhruv+Batra%2E+2017%2E+Deal+or+no+deal%3F+end%2Dto%2Dend+learning+for+negotiation+dialogues%2E+arXiv+preprint+arXiv%3A1706%2E05125%2E+%E2%80%94+%5BarXiv%3A1706%2E05125%5D%28http)
30. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, and 1 others. 2025. [Deepseek-v3](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/). 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
31. Yunbo Long, Liming Xu, Lukas Beckenbauer, Yuhan Liu, and Alexandra Brintrup. 2025. Evoemo: Towards evolved emotional policies for adversarial llm agents in multi-turn price negotiation. arXiv preprint arXiv:2509.04310. — [arXiv:2509.04310](https://arxiv.org/abs/2509.04310) [find](https://scholar.google.com/scholar?q=Yunbo+Long%2C+Liming+Xu%2C+Lukas+Beckenbauer%2C+Yuhan+Liu%2C+and+Alexandra+Brintrup%2E+2025%2E+Evoemo%3A+Towards+evolved+emotional+policies+for+adversarial+llm+agents+in+multi%2Dturn+price+negotiation%2E+arXiv+preprint)
32. N Gregory Mankiw, Ronald D Kneebone, Kenneth James McKenzie, and Nicholas Rowe. 2007. Principles of macroeconomics. [find](https://scholar.google.com/scholar?q=N+Gregory+Mankiw%2C+Ronald+D+Kneebone%2C+Kenneth+James+McKenzie%2C+and+Nicholas+Rowe%2E+2007%2E+Principles+of+macroeconomics%2E)
33. Abhinay Muthoo. 1999. Bargaining theory with applications. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Abhinay+Muthoo%2E+1999%2E+Bargaining+theory+with+applications%2E+Cambridge+University+Press%2E)
34. Georg Nöldeke and Klaus M Schmidt. 1995. Option contracts and renegotiation: a solution to the hold-up problem. The RAND Journal of Economics, pages 163–179. [find](https://scholar.google.com/scholar?q=Georg+N%C3%B6ldeke+and+Klaus+M+Schmidt%2E+1995%2E+Option+contracts+and+renegotiation%3A+a+solution+to+the+hold%2Dup+problem%2E+The+RAND+Journal+of+Economics%2C+pages+163%E2%80%93179%2E)
35. Dan Orr and Chris Guthrie. 2005. Anchoring, information, expertise, and negotiation: New insights from meta-analysis. Ohio St. J. on Disp. Resol., 21:597. [find](https://scholar.google.com/scholar?q=Dan+Orr+and+Chris+Guthrie%2E+2005%2E+Anchoring%2C+information%2C+expertise%2C+and+negotiation%3A+New+insights+from+meta%2Danalysis%2E+Ohio+St%2E+J%2E+on+Disp%2E+Resol%2E%2C+21%3A597%2E)
36. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
37. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
38. Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, and 1 others. 2023. [Discovering language model behaviors with model-written evaluations](https://md.research.elamur.ai/free/en/papers/perez-2022-discovering-language-model-behaviors-model/). In Findings of the Association for Computational Linguistics:…
39. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). Advances in Neural Information Processing Systems, 36:68539–68551.
40. Ryan Shea, Aymen Kallala, Xin Lucy Liu, Michael W. Morris, and Zhou Yu. 2024. ACE: A LLM-based negotiation coaching system. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12720–12749, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ryan+Shea%2C+Aymen+Kallala%2C+Xin+Lucy+Liu%2C+Michael+W%2E+Morris%2C+and+Zhou+Yu%2E+2024%2E+ACE%3A+A+LLM%2Dbased+negotiation+coaching+system%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Langua)
41. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, and 1 others. 2025. [Openai gpt-5 system card](https://md.research.elamur.ai/free/en/papers/singh-2025-openai-gpt-5-system-card/). arXiv preprint arXiv:2601.03267.
42. Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, and Tong Zhang. 2024. [Interpretable preferences via multi-objective reward modeling and mixture-of-experts](https://md.research.elamur.ai/free/en/papers/wang-2024-interpretable-preferences-multi-objective-reward/). arXiv preprint arXiv:2406.12845.
43. Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, and 1 others. 2021. [Ethical and social risks of harm from language models](https://md.research.elamur.ai/free/en/papers/weidinger-2021-ethical-social-risks-harm-language/). arXiv preprint arXiv:2112.04359.
44. Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, and Rui Wang. 2024. Measuring bargaining abilities of llms: A benchmark and a buyer-enhancement method. arXiv preprint arXiv:2402.15813. [find](https://scholar.google.com/scholar?q=Tian+Xia%2C+Zhiwei+He%2C+Tong+Ren%2C+Yibo+Miao%2C+Zhuosheng+Zhang%2C+Yang+Yang%2C+and+Rui+Wang%2E+2024%2E+Measuring+bargaining+abilities+of+llms%3A+A+benchmark+and+a+buyer%2Denhancement+method%2E+arXiv+preprint+arXiv%3A2402%2E)
45. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/), 2023. URL https://arxiv.org/abs/2210.03629. [↗](https://arxiv.org/abs/2210.03629)
46. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in Neural Information Processing Systems, 36:46595–46623.
47. Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, and Jiaxin Pei. 2025. The automated but risky game: Modeling agent-to-agent negotiations and transactions in consumer markets. In ICML 2025 [find](https://scholar.google.com/scholar?q=Shenzhe+Zhu%2C+Jiao+Sun%2C+Yi+Nian%2C+Tobin+South%2C+Alex+Pentland%2C+and+Jiaxin+Pei%2E+2025%2E+The+automated+but+risky+game%3A+Modeling+agent%2Dto%2Dagent+negotiations+and+transactions+in+consumer+markets%2E+In+ICML+2025)
48. Workshop on Reliable and Responsible Foundation Models. • Inventory: Includes product name, cost, price, and features. Cost is not visible to buyer. *Figure 6: Relation between the variables* [find](https://scholar.google.com/scholar?q=Workshop+on+Reliable+and+Responsible+Foundation+Models%2E+%E2%80%A2+Inventory%3A+Includes+product+name%2C+cost%2C+price%2C+and+features%2E+Cost+is+not+visible+to+buyer%2E+%2AFigure+6%3A+Relation+between+the+variables%2A)

*Updated 1 November 2026*