Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents

2026-02-08

AI Summary

This study addresses the challenge of sustaining indirect reciprocity among self-interested large language model (LLM) agents in the absence of reliable reputation mechanisms. To this end, the authors propose the Agentic Linguistic Gossip Network (ALIGN), a novel framework that introduces an open-ended linguistic gossip mechanism into multi-agent systems for the first time. Within ALIGN, agents generate and propagate gossip using hierarchical tonal expressions and leverage the reasoning capabilities of LLMs to perform decentralized credibility assessments and coordinate around social norms—all without altering their intrinsic incentives. Experimental results demonstrate that ALIGN substantially enhances indirect reciprocity and effectively identifies and excludes malicious cooperators. Moreover, LLMs with stronger reasoning abilities exhibit more strategic cooperation, whereas standard chat-oriented models tend toward excessive cooperation.

Technology Category

• Multiagent Systems: Agent Communication
• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Indirect reciprocity, which means helping those who help others, is difficult to sustain among decentralized, self-interested LLM agents without reliable reputation systems. We introduce Agentic Linguistic Gossip Network (ALIGN), an automated framework where agents strategically share open-ended gossip using hierarchical tones to evaluate trustworthiness and coordinate social norms. We demonstrate that ALIGN consistently improves indirect reciprocity and resists malicious entrants by identifying and ostracizing defectors without changing intrinsic incentives. Notably, we find that stronger reasoning capabilities in LLMs lead to more incentive-aligned cooperation, whereas chat models often over-cooperate even when strategically suboptimal. These results suggest that leveraging LLM reasoning through decentralized gossip is a promising path for maintaining social welfare in agentic ecosystems. Our code is available at https://github.com/shuhui-zhu/ALIGN.

Problem

• indirect reciprocity
• LLM agents
• reputation systems
• decentralized cooperation
• social norms

Innovation

• indirect reciprocity
• gossip mechanism
• LLM agents
• reputation system
• decentralized cooperation