# Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation

arXiv: https://arxiv.org/abs/2608.12125 · HTML: https://mlsanity.com/paper/2608.12125/

## Key facts

- No citing papers in the map yet (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 17 of its 58 references that are in the map.
- First posted on arXiv 12 Aug 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, 17 of 17)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life](https://mlsanity.com/paper/2410.02683/) (2024)
- [Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions](https://mlsanity.com/paper/2504.15236/) (2025)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios](https://mlsanity.com/paper/2412.03920/) (2024)
- [Mind the (Belief) Gap: Group Identity in the World of LLMs](https://mlsanity.com/paper/2503.02016/) (2025)
- [Functional Decision Theory: A New Theory of Instrumental Rationality](https://mlsanity.com/paper/1710.05060/) (2017)
- [Game Theory with Translucent Players](https://mlsanity.com/paper/1310.6438/) (2013)
- [The Computational Complexity of Single-Player Imperfect-Recall Games](https://mlsanity.com/paper/2305.17805/) (2023)
- [Imperfect-Recall Games: Equilibrium Concepts and Their Complexity](https://mlsanity.com/paper/2406.15970/) (2024)
- [A dataset of questions on decision-theoretic reasoning in Newcomb-like problems](https://mlsanity.com/paper/2411.10588/) (2024)
- [Computing Game Symmetries and Equilibria That Respect Them](https://mlsanity.com/paper/2501.08905/) (2025)
- [Representational Similarity and Model Behavior in Multi-Agent Interaction](https://mlsanity.com/paper/2606.07818/) (2026)

## Abstract (arXiv)

As LLM-based agents with user-instructed goals are becoming widely deployed, they increasingly encounter each other in strategic interactions, and face challenges of finding mutually beneficial outcomes. Prior literature has argued that cooperation problems such as the Prisoner's Dilemma are resolvable in settings where agents know they follow very similar decision making patterns, as for example in monocultural AI ecosystems. Following that line of work, this paper introduces the first framework for evaluating LLM decision making when agents are provided with graded similarity signals. Among our findings, we establish that different LLM models vary drastically in how they navigate similarity signals, with some modern models showing consistent behavior across cooperation problems, payoff structures, and prompt framing. Perhaps surprisingly, our experiments also show that the dataset based on which the similarity signal is computed has small to no impact on induced cooperation, and that LLM models systematically self-identify as highly similar when asked to evaluate another model's chain-of-thought reasoning by themselves. Finally, we develop an LLM-behavioral-game-theoretic model that captures some of their reasoning rationale, and show that it can support cooperative outcomes in equilibrium under sufficiently high similarity scores.