Reasoning-optimized LLMs reach at most 63.4% success across the five PDDL benchmarks, versus 97.9% for Fast Downward, and frequently produce plans that fail during execution.
Sadler, Wei-Lun Chao, and Yu Su
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
Reasoning-optimized LLMs reach at most 63.4% success across the five PDDL benchmarks, versus 97.9% for Fast Downward, and frequently produce plans that fail during execution.