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

arXiv: https://arxiv.org/abs/2602.07777 · HTML: https://mlsanity.com/paper/2602.07777/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 66 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Do LLM Agents Exhibit Social Behavior?](https://mlsanity.com/paper/2312.15198/) (2023)
- [Cultural Evolution of Cooperation among LLM Agents](https://mlsanity.com/paper/2412.10270/) (2024)
- [Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games](https://mlsanity.com/paper/2506.23276/) (2025)
- [Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity](https://mlsanity.com/paper/2408.04549/) (2024)
- [Learning to Negotiate via Voluntary Commitment](https://mlsanity.com/paper/2503.03866/) (2025)
- [Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game](https://mlsanity.com/paper/2506.06032/) (2025)
- [A Reputation System for Multi-Agent Marketplaces](https://mlsanity.com/paper/1905.08036/) (2019)

## Built on by (most cited first, 5 of 5)

- [Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes](https://mlsanity.com/paper/2606.17368/) (2026)
- [Incoherent Values? Probing LLM Preferences Through Parametric Variation](https://mlsanity.com/paper/2606.21102/) (2026)
- [I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems](https://mlsanity.com/paper/2603.18894/) (2026)
- [The Reciprocity Gradient](https://mlsanity.com/paper/2605.08323/) (2026)
- [Do AI Agents Gossip? Evaluative Talk in Human and AI-Agent Online Communities](https://mlsanity.com/paper/2610.20360/) (2026)

## Abstract (arXiv)

Indirect reciprocity, which means helping those who have helped others, is difficult to sustain among decentralized, self-interested LLM agents without reliable reputation systems. We address this challenge with the Agentic Linguistic Gossip Network (ALIGN), an automated framework that enables decentralized agents to form reputations, evaluate trustworthiness, and coordinate social norms by strategically sharing open-ended gossip with hierarchical tones. We demonstrate that ALIGN consistently improves indirect reciprocity and resists malicious entrants by identifying and ostracizing defectors. 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.