# Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches

arXiv: https://arxiv.org/abs/2510.05748 · HTML: https://mlsanity.com/paper/2510.05748/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 63 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 8 of 8)

- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents](https://mlsanity.com/paper/2406.06613/) (2024)
- [MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration](https://mlsanity.com/paper/2311.08562/) (2023)
- [TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs](https://mlsanity.com/paper/2410.10479/) (2024)
- [Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers](https://mlsanity.com/paper/2502.09053/) (2025)
- [Mastering Rate based Curriculum Learning](https://mlsanity.com/paper/2008.06456/) (2020)
- [PORT: Preference Optimization on Reasoning Traces](https://mlsanity.com/paper/2406.16061/) (2024)

## Built on by (most cited first, 4 of 4)

- [Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games](https://mlsanity.com/paper/2606.07790/) (2026)
- [Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation](https://mlsanity.com/paper/2605.01750/) (2026)
- [Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest](https://mlsanity.com/paper/2604.25088/) (2026)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)

## Abstract (arXiv)

Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word "cheap talk" channel increases cooperation from 0% to 96.7%, demonstrating communication as a robust coordination mechanism. In contrast, we find that curriculum learning is highly sensitive to design choices: our pedagogical curriculum through progressively complex games reduced agent payoffs by 27.4% in an Iterated Public Goods Game with Punishment, demonstrating that optimizing for short-term rationality can actively undermine alignment goals. Qualitative analysis reveals that curricula emphasizing defection-equilibrium games can induce "learned pessimism" in agents. These findings suggest that for coordination problems, simple communication protocols may be more reliable than experience-based training, and that curriculum design for social dilemmas requires careful attention to the strategic lessons embedded in game sequences.