# NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment

arXiv: https://arxiv.org/abs/2510.04368 · HTML: https://mlsanity.com/paper/2510.04368/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents](https://mlsanity.com/paper/2410.20746/) (2024)
- [A Simulation System Towards Solving Societal-Scale Manipulation](https://mlsanity.com/paper/2410.13915/) (2024)
- [LLM Agents for Bargaining with Utility-based Feedback](https://mlsanity.com/paper/2505.22998/) (2025)

## Built on by (most cited first, 3 of 3)

- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [LLM Agents in Law: Taxonomy, Applications, and Challenges](https://mlsanity.com/paper/2601.06216/) (2026)
- [No One Wins in Nuclear War: A Social Simulation of Military Decision-making](https://mlsanity.com/paper/2608.01868/) (2026)

## Abstract (arXiv)

We design and implement NegotiationGym, an API and user interface for configuring and running multi-agent social simulations focused upon negotiation and cooperation. The NegotiationGym codebase offers a user-friendly, configuration-driven API that enables easy design and customization of simulation scenarios. Agent-level utility functions encode optimization criteria for each agent, and agents can self-optimize by conducting multiple interaction rounds with other agents, observing outcomes, and modifying their strategies for future rounds.