EvoCorps: An Evolutionary Multi-Agent Framework for Depolarizing Online Discourse

2026-02-09

AI Summary

This study addresses the escalating social trust crisis and proliferation of misinformation driven by online discourse polarization, highlighting the limitations of existing static and reactive governance approaches in countering dynamically evolving adversarial amplification. To bridge this gap, the paper proposes a dynamic discourse governance framework grounded in evolutionary multi-agent systems, which— for the first time—formulates multi-agent coordination as a social game. By integrating role-based division of labor, retrieval-augmented collective cognition, fact generation, and multi-identity diffusion mechanisms, the framework shifts the paradigm from passive detection to proactive intervention. Implemented on the MOSAIC social AI simulation platform, the system employs closed-loop evolutionary learning to continuously optimize strategies in real time. Experimental results demonstrate significant improvements over adversarial baselines across key dimensions including affective polarization, opinion extremity, and argumentative rationality, thereby validating its efficacy in dynamic depolarization.

Technology Category

• Multiagent Systems: Adversarial Agents
• Game Theory and Economic Paradigms: Adversarial Learning
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Polarization in online discourse erodes social trust and accelerates misinformation, yet technical responses remain largely diagnostic and post-hoc. Current governance approaches suffer from inherent latency and static policies, struggling to counter coordinated adversarial amplification that evolves in real-time. We present EvoCorps, an evolutionary multi-agent framework for proactive depolarization. EvoCorps frames discourse governance as a dynamic social game and coordinates roles for monitoring, planning, grounded generation, and multi-identity diffusion. A retrieval-augmented collective cognition core provides factual grounding and action--outcome memory, while closed-loop evolutionary learning adapts strategies as the environment and attackers change. We implement EvoCorps on the MOSAIC social-AI simulation platform for controlled evaluation in a multi-source news stream with adversarial injection and amplification. Across emotional polarization, viewpoint extremity, and argumentative rationality, EvoCorps improves discourse outcomes over an adversarial baseline, pointing to a practical path from detection and post-hoc mitigation to in-process, closed-loop intervention. The code is available at https://github.com/ln2146/EvoCorps.

Problem

• online polarization
• misinformation
• adversarial amplification
• discourse governance
• social trust

Innovation

• evolutionary multi-agent framework
• proactive depolarization
• retrieval-augmented collective cognition
• closed-loop evolutionary learning
• dynamic social game