# More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration

arXiv: https://arxiv.org/abs/2604.07821 · HTML: https://mlsanity.com/paper/2604.07821/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 60 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [Cultural Evolution of Cooperation among LLM Agents](https://mlsanity.com/paper/2412.10270/) (2024)
- [Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma](https://mlsanity.com/paper/2501.16173/) (2025)
- [Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games](https://mlsanity.com/paper/2506.23276/) (2025)
- [Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/2112.10859/) (2021)
- [Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.10733/) (2023)
- [Observation Interference in Partially Observable Assistance Games](https://mlsanity.com/paper/2412.17797/) (2024)
- [Humans expect rationality and cooperation from LLM opponents in strategic games](https://mlsanity.com/paper/2505.11011/) (2025)

## Built on by (most cited first, 7 of 7)

- [CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments](https://mlsanity.com/paper/2606.06399/) (2026)
- [The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate](https://mlsanity.com/paper/2608.22152/) (2026)
- [Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives](https://mlsanity.com/paper/2607.22188/) (2026)
- [ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures](https://mlsanity.com/paper/2609.16986/) (2026)
- [From Certain Doom to Survival: Agent-Driven Self-Governance in LLM Agent Societies](https://mlsanity.com/paper/2609.22600/) (2026)
- [The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces](https://mlsanity.com/paper/2609.32825/) (2026)
- [Multi-agent discussion gains less when dissent is withheld](https://mlsanity.com/paper/2609.38324/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents increasingly coordinate in multi-agent systems, yet we lack an understanding of where and why cooperation fails. Many real-world coordination problems are not social dilemmas: helping others -- sharing documentation, unblocking a teammate -- costs the helper almost nothing while producing substantial collective benefit. Whether LLM agents cooperate in this regime, where helping is free and they are explicitly instructed to do so, remains unknown. We build a turn-based multi-agent environment that strips away all strategic complexity, making cooperation costless and trivially optimal. Across eight widely used LLMs, capability does not predict cooperation: OpenAI o3 reaches only 17% of optimal collective performance while the weaker o3-mini reaches 50%, despite identical instructions to maximize group revenue. Using a causal decomposition that automates one side of agent communication, we separate cooperation failures from competence failures, and find that several capable models actively withhold information despite gaining nothing from withholding. Targeted interventions address each mode: explicit protocols roughly double the performance of competence-limited models, while small sharing incentives unlock cooperation-limited ones. Our results suggest that scaling intelligence alone will not solve coordination in multi-agent systems, and will require deliberate cooperative design, even when helping costs nothing.