Problem
Research questions and friction points this paper is trying to address.
optimal classical planning
admissible heuristics
learned heuristics
domain-dependent heuristics
A* search
LLM-Evolved Pattern Generators for Optimal Classical Planning
🤖 AI Summary
Existing learned heuristics often lack admissibility guarantees, rendering them unsuitable for optimal classical planning. This work proposes a large language model–driven evolutionary program synthesis framework that automatically generates interpretable programs tailored to individual planning domains. These programs construct pattern collections and, when combined with saturated cost partitioning, yield admissible, domain-specific heuristics. To the best of our knowledge, this is the first approach to produce learned, admissible, domain-dependent heuristics, preserving the optimality of A* while substantially reducing per-state evaluation overhead. Empirical results demonstrate that the method achieves coverage comparable to state-of-the-art domain-independent heuristics across multiple planning domains, offering both computational efficiency and strong theoretical guarantees.
📝 Abstract
Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning. Existing approaches, however, focus on improving search guidance rather than guaranteeing admissibility, which makes them unsuitable for optimal classical planning. We present the first method for learning domain-dependent heuristics that are admissible by design and thus preserve the optimality guarantees of A* search. Instead of learning a direct mapping from states to heuristic values, we learn to construct abstractions that induce admissible heuristics. We use an LLM-driven evolutionary program-synthesis framework to obtain, for each domain, a program that produces a pattern collection for any task in that domain, and we combine the resulting patterns admissibly via saturated cost partitioning. Empirically, the learned programs encode interpretable domain-specific insights, run with negligible overhead at test time and yield heuristics that match the coverage of state-of-the-art domain-independent baselines on several domains while evaluating each state substantially faster.
Innovation
Methods, ideas, or system contributions that make the work stand out.
admissible heuristics
LLM-driven program synthesis
pattern generation
optimal classical planning
saturated cost partitioning
🔎 Similar Papers
No similar papers found.
