A hierarchical multi-agent framework with GPT-4o generates escape room puzzle images that are judged more solvable and less shortcut-prone than vanilla text-to-image outputs.
Puzzlevqa: Diagnosing mul- timodal reasoning challenges of language models with ab- stract visual patterns
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles
A hierarchical multi-agent framework with GPT-4o generates escape room puzzle images that are judged more solvable and less shortcut-prone than vanilla text-to-image outputs.