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

2025/10/05 by Shashank Mangla, Mangla, Shashank, Chris Hokamp +11
Computer Science · Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #Evacuation and Crowd Dynamics #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA) #Simulation Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2510.04368

openalex publication_date 2025/10/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• LLM Agents for Bargaining with Utility-based Feedback
• ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents
• A Simulation System Towards Solving Societal-Scale Manipulation
• Large Language Models Cannot Self-Correct Reasoning Yet
• AIKernel Semantic DSL Compiler and Deterministic Agent Execution Architecture
• Improving Factuality and Reasoning in Language Models through Multiagent Debate
• Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
• Reflexion: Language Agents with Verbal Reinforcement Learning
• The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets
• Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs

Related

• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
• An agent-based negotiation model and its implementation in Repast
• SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
• How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
• Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactions