When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability
Key takeaway
Large language models (LLMs) struggle with classical planning, but benchmarks rarely distinguish structural difficulty from the difficulty of interpreting symbolic vocabulary.
Why it's on PDOOM
PDOOM selected this story for its alignment & control signals: Interpretability.
InterpretabilityFrom ArXiv cs.AI
Large language models (LLMs) struggle with classical planning, but benchmarks rarely distinguish structural difficulty from the difficulty of interpreting symbolic vocabulary. We examine seven STRIPS domains with BFS-optimal plan lengths. For predicting structural difficulty without solving an instance, the zero-training delete-relaxation heuristic $h_{\mathrm{add}}$ outperforms learned alternatives on held-out domains (mean Spearman $|\rho|=0.931$
By Mayukh Debnath, Adeyinka Adedigba, Rammohan Mallipeddi