# M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games

arXiv: https://arxiv.org/abs/2601.08462 · HTML: https://mlsanity.com/paper/2601.08462/

## Key facts

- Cited by 8 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 26 of its 75 references that are in the map.
- First posted on arXiv 13 Jan 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, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Inequity aversion improves cooperation in intertemporal social dilemmas](https://mlsanity.com/paper/1803.08884/) (2018)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents](https://mlsanity.com/paper/2406.06613/) (2024)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models](https://mlsanity.com/paper/2404.12387/) (2024)
- [Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents](https://mlsanity.com/paper/2305.13455/) (2023)
- [Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction](https://mlsanity.com/paper/2407.13943/) (2024)
- [ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination](https://mlsanity.com/paper/2310.05208/) (2023)
- [GAMEBoT: Transparent Assessment of LLM Reasoning in Games](https://mlsanity.com/paper/2412.13602/) (2024)
- [LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions](https://mlsanity.com/paper/2506.12666/) (2025)
- [AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents](https://mlsanity.com/paper/2401.06509/) (2024)

## Built on by (most cited first, 8 of 8)

- [WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking](https://mlsanity.com/paper/2603.27343/) (2026)
- [Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents](https://mlsanity.com/paper/2606.08200/) (2026)
- [When Does Personality Composition Matter for Multi-Agent LLM Teams?](https://mlsanity.com/paper/2606.27443/) (2026)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)
- [Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents](https://mlsanity.com/paper/2606.00476/) (2026)
- [Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents](https://mlsanity.com/paper/2608.07490/) (2026)
- [AI Alignment through a Game-theoretic Lens: A Survey](https://mlsanity.com/paper/2608.27910/) (2026)
- [Benchmarking large language model agent societies against human behavioural distributions](https://mlsanity.com/paper/2608.28182/) (2026)

## Abstract (arXiv)

Existing benchmarks for LLM agents' social behavior typically focus on a single capability dimension and evaluate only behavioral outcomes, overlooking process signals from reasoning and communication. We present M3-BENCH, a benchmark of 24 mixed-motive games with a process-aware evaluation framework spanning three complementary views: Behavioral Trajectory Analysis (BTA), Reasoning Process Analysis (RPA), and Communication Content Analysis (CCA). Evaluating 11 frontier LLMs and a human baseline, M3-BENCH reveals substantial differences in social competence that outcome-only evaluation misses. In particular, we identify an "overthink-undercommunicate" pattern: reasoning models achieve strong internal deliberation scores but often fail to translate them into effective social communication. Although top models can surpass humans on task outcomes, humans exhibit markedly higher cross-view consistency, suggesting that current LLM agents still lack the behavioral coherence characteristic of human social competence. Our analysis further shows that the three-view decomposition surfaces safety-relevant risks, such as cooperative behavior paired with latent opportunistic reasoning, that remain hidden under outcome-only metrics.