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

Shashank Mangla; Chris Hokamp; Jack Boylan; Demian Gholipour Ghalandari; Yuuv Jauhari; Lauren Cassidy; Oisin Duffy

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

Multiagent Systems 2025-10-07 v1 Artificial Intelligence

Authors: Shashank Mangla , Chris Hokamp , Jack Boylan , Demian Gholipour Ghalandari , Yuuv Jauhari , Lauren Cassidy , Oisin Duffy

View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

multi-agent systems multi-agent reinforcement learning simulation

Cite

@article{arxiv.2510.04368,
  title  = {NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment},
  author = {Shashank Mangla and Chris Hokamp and Jack Boylan and Demian Gholipour Ghalandari and Yuuv Jauhari and Lauren Cassidy and Oisin Duffy},
  journal= {arXiv preprint arXiv:2510.04368},
  year   = {2025}
}

Comments

SocialSim Workshop at COLM 2025

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

Abstract

Keywords

Cite

Comments

Related papers