Reasoning models' Towers of Hanoi failures persist under stepwise prompting, while River Crossing failures mostly vanish when tests are restricted to solvable configurations.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking the Illusion of Thinking
Reasoning models' Towers of Hanoi failures persist under stepwise prompting, while River Crossing failures mostly vanish when tests are restricted to solvable configurations.