# Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation

Source: [Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-28T05:00:04.914Z

Authors: Weiwei Fang, Lin Li, Kaize Shi, Yu Yang, Jianwei Zhang

Published: 2026-03-26T03:06:36.000Z

## Abstract

High-fidelity social simulation is pivotal for addressing complex Web societal challenges, yet it demands agents capable of authentically replicating the dynamic spectrum of human interaction. Current LLM-based multi-agent frameworks, however, predominantly adhere to static interaction topologies, failing to capture the fluid oscillation between cooperative knowledge synthesis and competitive critical reasoning seen in real-world scenarios. This rigidity often leads to unrealistic \`\`groupthink'' or unproductive deadlocks, undermining the credibility of simulations for decision support. To bridge this gap, we propose \\textit{BEACOF}, a \\textit{belief-driven adaptive collaboration framework} inspired by Perfect Bayesian Equilibrium (PBE). By modeling social interaction as a dynamic game of incomplete information, BEACOF rigorously addresses the circular dependency between collaboration type selection and capability estimation. Agents iteratively refine probabilistic beliefs about peer capabilities and autonomously modulate their collaboration strategy, thereby ensuring sequentially rational decisions under uncertainty. Validated across adversarial (judicial), open-ended (social) and mixed (medical) scenarios, BEACOF prevents coordination failures and fosters robust convergence toward high-quality solutions, demonstrating superior potential for reliable social simulation. Source codes and datasets are publicly released at: https://github.com/WUT-IDEA/BEACOF.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Judicial Conflict Resolution on AgentsCourt + China Judgements Online](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md>): Judicial Conflict Resolution; AgentsCourt + China Judgements Online; Legal Article Precision: 73.33.

- [Social Inclusion on PersonaChat](<https://www.sota2.com/research/sota/social-inclusion-on-personachat.md>): Social Inclusion; PersonaChat; Diversity: 41.52.

- [Professional Consensus Building on MedQA](<https://www.sota2.com/research/sota/professional-consensus-building-on-medqa.md>): Professional Consensus Building; MedQA; MedQA Accuracy: 84.67.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.24973>)

[PDF](<https://arxiv.org/pdf/2603.24973.pdf>)