Abstract:Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existing benchmarks only partially test this ability. Egocentric video datasets capture realistic human activities but remain passive, while interactive simulators support execution but rely on synthetic scenes and hand-crafted dynamics, introducing a sim-to-real gap and often assuming fully observable state. We introduce Ego2World, an executable benchmark that turns egocentric cooking videos into executable symbolic worlds governed by graph-transition rules. Built on HD-EPIC, Ego2World derives reusable transition rules from video annotations and executes them in a hidden symbolic world graph. During evaluation, the simulator maintains the hidden world graph, while the agent plans over its own partial belief graph using only local observations and execution feedback. This separation forces agents to update memory and replan without observing the true world state. Experiments show that action-overlap scores overestimate physical-state success, and that persistent belief memory improves task completion while reducing repeated visual exploration -- suggesting that belief maintenance should be a first-class target of embodied-agent evaluation.
| Comments: | Project page: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.13335 [cs.AI] |
| (or arXiv:2605.13335v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13335 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qinchuan Cheng [view email]
[v1]
Wed, 13 May 2026 10:53:15 UTC (3,617 KB)