Frontier LLMs complete few of 25 Infocom text adventures even when given the official hint booklets, revealing a weakness in sustained long-context reasoning.
This is a fake!
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TextQuests: How Good are LLMs at Text-Based Video Games?
Frontier LLMs complete few of 25 Infocom text adventures even when given the official hint booklets, revealing a weakness in sustained long-context reasoning.