# Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models

arXiv: https://arxiv.org/abs/2608.20975 · HTML: https://mlsanity.com/paper/2608.20975/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 29 of its 66 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [ToMBench: Benchmarking Theory of Mind in Large Language Models](https://mlsanity.com/paper/2402.15052/) (2024)
- [NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding](https://mlsanity.com/paper/2404.13627/) (2024)
- [Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction](https://mlsanity.com/paper/2407.13943/) (2024)
- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [Distilling Internet-Scale Vision-Language Models into Embodied Agents](https://mlsanity.com/paper/2301.12507/) (2023)
- [MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models](https://mlsanity.com/paper/2410.09542/) (2024)
- [Playing the Werewolf game with artificial intelligence for language understanding](https://mlsanity.com/paper/2302.10646/) (2023)
- [SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions](https://mlsanity.com/paper/2506.23046/) (2025)
- [EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective](https://mlsanity.com/paper/2410.06195/) (2024)
- [On the robustness of multimodal language model towards distractions](https://mlsanity.com/paper/2502.09818/) (2025)
- [Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2603.14184/) (2026)

## Abstract (arXiv)

Effective social interaction requires agents to translate mental state inferences into coordinated behavioral signals across verbal and nonverbal channels simultaneously. Yet existing benchmarks evaluate theory of mind (ToM) reasoning and embodied behavior in isolation, leaving unmeasured the gap between social inference and social action. We introduce MOSAIC (Multimodal Orchestration of Social Action, Inference, and Communication), a controlled benchmark in which two embodied agents interact across cooperative and competitive scenarios requiring integration of verbal statements, spatial trajectories, gaze direction, and facial expression under systematically varied ToM constraints. Evaluating 13 models, including 11 VLMs, across 200 trials per model, we find that VLMs fail to produce behaviors consistent with the expected outcomes under ToM-order constraints, and that imposing explicit ToM-order constraints produces no reliable behavioral change aligned with the specified reasoning level. Signal-level analysis reveals two sequential bottlenecks: most models cannot produce directionally coherent nonverbal signals, and even when signals are present, VLM agents fail to interpret others behaviors and react to them. PCM-LLM, included as a structured architectural reference point with an explicit ToM module, succeeds across all conditions, suggesting that explicit belief-action coupling is a sufficient ingredient for this class of tasks.