# GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs

arXiv: https://arxiv.org/abs/2606.04184 · HTML: https://mlsanity.com/paper/2606.04184/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 14 of its 54 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 14 of 14)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models](https://mlsanity.com/paper/2505.21523/) (2025)
- [SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs](https://mlsanity.com/paper/2410.13648/) (2024)
- [NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding](https://mlsanity.com/paper/2404.13627/) (2024)
- [SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions](https://mlsanity.com/paper/2506.23046/) (2025)
- [Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective](https://mlsanity.com/paper/2504.10839/) (2025)
- [MOMENTS: A Comprehensive Multimodal Benchmark for Theory of Mind](https://mlsanity.com/paper/2507.04415/) (2025)
- [EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos](https://mlsanity.com/paper/2503.22152/) (2025)
- [SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments](https://mlsanity.com/paper/2505.23713/) (2025)
- [Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions](https://mlsanity.com/paper/2510.27195/) (2025)
- [Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity](https://mlsanity.com/paper/2410.06151/) (2024)
- [The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind](https://mlsanity.com/paper/2506.20664/) (2025)
- [CaveAgent: Transforming LLMs into Stateful Runtime Operators](https://mlsanity.com/paper/2601.01569/) (2026)

## Built on by (most cited first, 1 of 1)

- [Unified Hallucination Fuzzing for Multimodal Large Language Models](https://mlsanity.com/paper/2608.07525/) (2026)

## Abstract (arXiv)

True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental states interact and crystallize into group-level outcomes. Despite notable progress in individual-level Theory of Mind (ToM) reasoning, existing multimodal large language models fail at this broader task. Collective behavior emerges non-linearly from social tensions, conformity dynamics, and structural constraints, meaning it cannot be recovered by merely summing individual intentions. We present GroupToM-Bench, the first multimodal benchmark for group-level ToM, built around a causal chain spanning micro-level BDI states (belief, desire, intention), meso-level group tension and structural constraints, and macro-level outcome prediction and mechanistic attribution. To probe this full arc, we develop a seven-level cognitive audit framework. Experiments reveal a gap between current models and human baselines, highlighting a failure to process social structures and non-linear collective dynamics.