{"ID":2836158,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20937","arxiv_id":"2511.20937","title":"ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction","abstract":"Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? We introduce ENACT, a benchmark that casts evaluation of embodied cognition as world modeling from egocentric interaction in a visual question answering (VQA) format. Framed as a partially observable Markov decision process (POMDP) whose actions are scene graph changes, ENACT comprises two complementary sequence reordering tasks: forward world modeling (reorder shuffled observations given actions) and inverse world modeling (reorder shuffled actions given observations). While conceptually simple, solving these tasks implicitly demands capabilities central to embodied cognition-affordance recognition, action-effect reasoning, embodied awareness, and interactive, long-horizon memory from partially observable egocentric input, while avoiding low-level image synthesis that could confound the evaluation. We provide a scalable pipeline that synthesizes QA pairs from robotics simulation (BEHAVIOR) and evaluates models on 8,972 QA pairs spanning long-horizon home-scale activities. Experiments reveal a performance gap between frontier VLMs and humans that widens with interaction horizon. Models consistently perform better on the inverse task than the forward one and exhibit anthropocentric biases, including a preference for right-handed actions and degradation when camera intrinsics or viewpoints deviate from human vision. Website at https://enact-embodied-cognition.github.io/.","short_abstract":"Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? We introduce ENACT, a benchmark that casts evaluation...","url_abs":"https://arxiv.org/abs/2511.20937","url_pdf":"https://arxiv.org/pdf/2511.20937v1","authors":"[\"Qineng Wang\",\"Wenlong Huang\",\"Yu Zhou\",\"Hang Yin\",\"Tianwei Bao\",\"Jianwen Lyu\",\"Weiyu Liu\",\"Ruohan Zhang\",\"Jiajun Wu\",\"Li Fei-Fei\",\"Manling Li\"]","published":"2025-11-26T00:06:02Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.CV\",\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}