{"ID":2860415,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04368","arxiv_id":"2510.04368","title":"NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment","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.","short_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-le...","url_abs":"https://arxiv.org/abs/2510.04368","url_pdf":"https://arxiv.org/pdf/2510.04368v1","authors":"[\"Shashank Mangla\",\"Chris Hokamp\",\"Jack Boylan\",\"Demian Gholipour Ghalandari\",\"Yuuv Jauhari\",\"Lauren Cassidy\",\"Oisin Duffy\"]","published":"2025-10-05T21:23:21Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.AI\"]","methods":"[]","has_code":false}