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

• URL: http://arxiv.org/abs/2606.04184v1
• Date: Tue, 02 Jun 2026 20:06:32 GMT
• Title: GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
• Abstract summary: We present GroupToM-Bench, the first multimodal benchmark for group-level Theory of Mind (ToM) reasoning.<n>We build 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 attribution.<n>Experiments reveal a gap between current models and human baselines, highlighting a failure to process social structures and non-linear collective dynamics.
• Score: 22.02836146038364
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models [0.509780930114934]
  Effective social interaction requires agents to translate mental state inferences into coordinated behavioral signals across verbal and nonverbal channels simultaneously.<n>We introduce MOSAIC, a benchmark in which two embodied agents interact across cooperative and competitive scenarios.<n>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.
  arXiv  Detail & Related papers  (2026-08-21T10:55:14Z)
• Scaling Behavior Foundation Model for Humanoid Robots [77.31115920959364]
  Behavior Foundation Models (BFMs) have emerged as a promising solution to address challenges by leveraging large-scale behavioral data.<n>We show that our approach yields significant improvements in control fidelity and task generalization.<n>These results establish BFM as a principled and effective foundation for scalable and general-purpose humanoid control.
  arXiv  Detail & Related papers  (2026-07-16T16:08:27Z)
• Towards Predictive, Aligned, and Scalable Robot Learning [11.830982964522605]
  We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.<n>We study latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization.<n>Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines.
  arXiv  Detail & Related papers  (2026-07-13T08:53:34Z)
• Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification [8.288757798319624]
  Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded.<n>We propose CAREB-MAS, a multi-agent framework grounded in Affect Control Theory, Social Identity Theory, and Durkheimian collective affect.<n>Agents reason through an emotion-ethics-belief chain and maintain dynamically evolving egocentric identities.
  arXiv  Detail & Related papers  (2026-06-22T14:25:36Z)
• MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation [51.824145170051516]
  MobEvolve is a self-evolving framework for human mobility generation.<n>It employs an agent to iteratively evolve its internal logic.<n>It significantly outperforms state-of-the-art deep generative and LLM-based methods.
  arXiv  Detail & Related papers  (2026-06-01T03:46:25Z)
• World Action Models: The Next Frontier in Embodied AI [123.5787299299832]
  Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning.<n>They learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention.<n>A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.
  arXiv  Detail & Related papers  (2026-05-12T13:10:52Z)
• Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation [38.13720312846963]
  We study diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics.<n>We characterize these outcomes as collective failures emerging from structural coupling.<n>Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency.
  arXiv  Detail & Related papers  (2026-04-20T09:27:49Z)
• SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models [86.19617358080016]
  Social Omni is a benchmark that operationalizes the evaluation of conversational interactivity across three core dimensions.<n>Social Omni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances.<n>Our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions.
  arXiv  Detail & Related papers  (2026-03-17T17:58:44Z)
• The Trinity of Consistency as a Defining Principle for General World Models [106.16462830681452]
  General World Models are capable of learning, simulating, and reasoning about objective physical laws.<n>We propose a principled theoretical framework that defines the essential properties requisite for a General World Model.<n>Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.
  arXiv  Detail & Related papers  (2026-02-26T16:15:55Z)
• Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling [11.987225062711692]
  PRISM is a model-agnostic system that augments Large Language Models with dynamic On-the-fly Epistemic Graphs.<n>On three creativity benchmarks, PRISM achieves state-of-the-art novelty and significantly expands distributional diversity.<n>Results demonstrate that PRISM successfully uncovers correct long-tail diagnoses that standard LLM miss.
  arXiv  Detail & Related papers  (2026-02-24T19:38:31Z)
• PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation [24.36529339525981]
  We introduce the Personality-Refracted Intelligent Simulation Model (PRISM) for continuous emotional evolution with a personalityconditional partially observable Markov decision process.<n>PRISM achieves superior consistency with human ground truth, outperforming standard homogeneous and Big Five benchmarks.<n>This framework effectively replicates emergent phenomena such as rational suppression and affective resonance, offering a robust tool for analyzing complex social media ecosystems.
  arXiv  Detail & Related papers  (2025-12-22T23:31:49Z)
• FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning [52.88164697048371]
  We introduce FysicsWorld, the first unified full-modality benchmark that supports bidirectional input-output across image, video, audio, and text.<n>FysicsWorld encompasses 16 primary tasks and 3,268 curated samples, aggregated from over 40 high-quality sources.
  arXiv  Detail & Related papers  (2025-12-14T16:41:29Z)
• World Models Should Prioritize the Unification of Physical and Social Dynamics [57.91940497010114]
  This paper argues that the systematic, bidirectional unification of physical and social predictive capabilities is the next crucial frontier for world model development.<n>We contend that comprehensive world models must holistically integrate objective physical laws with the subjective, evolving, and context-dependent nature of social dynamics.
  arXiv  Detail & Related papers  (2025-10-24T07:42:37Z)
• Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner [32.33827730707331]
  We propose a scalable Bayesian ToM planner that decomposes ToM reasoning into stepwise Bayesian updates.<n>Our framework introduces weak-to-strong control, allowing smaller language models to specialize in ToM-specific likelihood estimation.<n>Our method achieves a 4.6% accuracy improvement over state-of-the-art techniques on multimodal ToM benchmarks.
  arXiv  Detail & Related papers  (2025-06-02T04:23:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.