arXiv：cs.AI· Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Shijie Li·· 5 小时前AI 评分42
Ego2World：将第一视角烹饪视频编译为可执行世界以进行信念状态规划
Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
AI 导读
Ego2World 是一个将标注烹饪活动转化为部分可观测下可执行规划环境的基准，其编译器把源步骤和对象链接为符号动作规则、持久世界状态与显式任务条件。在 105 项任务上评估六种规划器显示，被接受的操作往往未能达成任务目标。一项 Qwen-Plus 配对研究中，持久信念将动作有效性提升 4.15 个百分点，视觉查询尝试减少 90.27%，但 token 用量更高且未检测到完成度提升。
正文
Abstract:Egocentric videos capture how people carry out everyday activities, yet testing an agent requires evaluating the consequences of actions it chooses itself. We introduce Ego2World, a benchmark that turns annotated cooking activities into executable planning environments under partial observation. Its compiler links source steps and objects to symbolic action rules, persistent world states, and explicit task conditions, so researchers can execute an agent's proposed actions and check their outcomes. World state and agent belief are maintained separately, enabling controlled studies of planning and information reuse across continuing tasks. Evaluating six planners on 105 tasks shows that accepted operations often leave task goals unmet. Execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment. In a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher token use and no detected completion gain. Ego2World provides a reusable testbed for tracing how planning and memory choices affect execution, observation demand, and task attainment, connecting recorded human activity to the development and evaluation of interactive agents.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02715 [cs.AI] |
| (or arXiv:2610.02715v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02715 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qinchuan Cheng [view email]
[v1]
Fri, 2 Oct 2026 02:51:03 UTC (2,382 KB)
来源：arXiv：cs.AI · arxiv.org