Paper Overview
Research Area: ML Authors: Katharina Stein, Chaahat Jain, Jörg Hoffmann, Alexander Koller Published: 2026-09-25 arXiv: 2609.27105
Abstract
Generalized planning aims to compute a plan that solves all instances of a planning domain. Recent work has used LLMs to automatically generate and debug such generalized plans in the form of Python programs and achieved perfect test data coverage for several domains. However, whether these generalized plans are actually complete, i.e. solve all instances of the domain, could only be determined by manual evaluation.
Here, we present an approach for automatically generating generalized plans in Lean together with proofs of their completeness relative to a specification of the domain constraints provided as input. We introduce a semantic-preserving PDDL-to-Lean conversion, and use an LLM to generate both the generalized plan and the formal proof that it solves every instance satisfying the domain constraints. The correctness of the completeness proof is verified by the Lean kernel.
Results
- Evaluated with GPT-5.6-Sol on 13 commonly used benchmark domains
- 12 of 13 domains yielded generalized plans with valid completeness proofs
- A significant step toward provably complete automated generalized planning
*Auto-collected 2026-09-25*