The results reveal a consistent pattern: Full MWM achieves the strongest decision-prediction performance for every evaluated model. Removing the mental channel degrades all models. The gains are largest in interpersonal situations, where hidden beliefs, intentions, emotions, and norms determine the action. Explicit intermediate structure substantially improves multimodal reasoning. The largest remaining bottleneck is transition simulation: predicting how an action changes the coupled physical–mental world.
Paper page - Mental World Modeling… In this work, we conceptualize Agent-Centric Interactive World Proxies, shifting the fundamental paradigm from physical state transitions to agent-usable information transitions, such as execution outcomes, retrieved experiences or skills, and verification signals, broadening the scope of world mod… …
… The largest remaining bottleneck is transition simulation : predicting how an action changes the coupled physical–mental world. Why does this matter? A physically possible action is not necessarily the action a person will take. …
… View arXiv page View PDF Project page GitHub 51 Add to collection Community ODEWorld explores continuous-time world modeling by learning a latent ODE velocity field instead of discrete-time transitions. …
… AI-generated summary The discovery of novel materials is critical for global energy and quantum technology transitions. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Disaggregated inference architectures physically separate prefill and decode phase s onto distinct GPU pools , creating competing "agents" that share a fixed hardware budget. …
… Across 14 MLLMs, even the strongest model reaches only 65.6% transition validity and 66.3% requirement coverage, and visual quality is no proxy for behavior Qwen3.6-35B-A3B on Markdown: V=80.8 yet T=15.5 . …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execut… …
… We further propose PICA, a physically informed contact-aware training mechanism that injects physical signals into policy learning without tactile or force feedback, improving robustness and task success under changing contact loads. …
… OGPP is motivated by two insights: i particles are defined up to permutation symmetries, so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; and ii particles live in physical space, so the flow terminal velocity has physical meaning and can encode geomet… …
… Second, a memory bottleneck: recency-biased history compression in existing world models discards the event-transition frames that causally determine subsequent object states, leading to an action-forgetting pathology . …