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

TL;DR

EvoCorps is an innovative evolutionary multi-agent framework designed to proactively reduce polarization in online discourse by dynamically adapting strategies in real-time to counter adversarial amplification.

Contribution

It introduces a novel proactive depolarization approach using an evolutionary multi-agent system with a collective cognition core for real-time discourse moderation.

Findings

EvoCorps outperforms baseline methods in reducing polarization metrics.

The framework adapts strategies effectively in changing adversarial environments.

Controlled experiments demonstrate improved discourse quality across multiple polarization indicators.

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.