VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910970216972288 |
|---|---|
| author | Lim, Seungwon Kim, Sungwoong Yu, Jihwan Lee, Sungjae Chung, Jiwan Yu, Youngjae |
| author_facet | Lim, Seungwon Kim, Sungwoong Yu, Jihwan Lee, Sungjae Chung, Jiwan Yu, Youngjae |
| contents | Escape rooms present a unique cognitive challenge that demands exploration-driven planning: with the sole instruction to 'escape the room', players must actively search their environment, collecting information, and finding solutions through repeated trial and error. Motivated by this, we introduce VisEscape, a benchmark of 20 virtual escape rooms specifically designed to evaluate AI models under these challenging conditions, where success depends not only on solving isolated puzzles but also on iteratively constructing and refining spatial-temporal knowledge of a dynamically changing environment. On VisEscape, we observe that even state-of-the-art multi-modal models generally fail to escape the rooms, showing considerable variation in their progress and problem-solving approaches. We find that integrating memory management and reasoning contributes to efficient exploration and enables successive hypothesis formulation and testing, thereby leading to significant improvements in dynamic and exploration-driven environments |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14427 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms Lim, Seungwon Kim, Sungwoong Yu, Jihwan Lee, Sungjae Chung, Jiwan Yu, Youngjae Artificial Intelligence Escape rooms present a unique cognitive challenge that demands exploration-driven planning: with the sole instruction to 'escape the room', players must actively search their environment, collecting information, and finding solutions through repeated trial and error. Motivated by this, we introduce VisEscape, a benchmark of 20 virtual escape rooms specifically designed to evaluate AI models under these challenging conditions, where success depends not only on solving isolated puzzles but also on iteratively constructing and refining spatial-temporal knowledge of a dynamically changing environment. On VisEscape, we observe that even state-of-the-art multi-modal models generally fail to escape the rooms, showing considerable variation in their progress and problem-solving approaches. We find that integrating memory management and reasoning contributes to efficient exploration and enables successive hypothesis formulation and testing, thereby leading to significant improvements in dynamic and exploration-driven environments |
| title | VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.14427 |