Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.08462 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918424718868480 |
|---|---|
| author | Xie, Sixiong Shi, Zhuofan Shen, Haiyang Ma, Yun Jing, Xiang |
| author_facet | Xie, Sixiong Shi, Zhuofan Shen, Haiyang Ma, Yun Jing, Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08462 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games Xie, Sixiong Shi, Zhuofan Shen, Haiyang Ma, Yun Jing, Xiang Artificial Intelligence 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. |
| title | M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08462 |