The paper claims that the reported accuracy collapse of reasoning models on planning puzzles is mostly caused by output length limits and unsolvable benchmark instances, not by reasoning failure.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
The paper claims that the reported accuracy collapse of reasoning models on planning puzzles is mostly caused by output length limits and unsolvable benchmark instances, not by reasoning failure.