PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
2026-08-17 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors found that large language models (LLMs) often make mistakes when creating long-term plans. To fix this, they built PDDLCoder, a system that turns natural language into a special planning language (PDDL) through repeated checking and fixing. They also made a new test set called NL-pddlgym to automatically check if plans really work. Their system made better and more reliable plans than older methods or direct LLM planning. This shows their approach is good for helping computers plan actions and provides a new way to test future methods.
Large Language ModelsLong-Horizon PlanningPlanning Domain Definition Language (PDDL)Symbolic PlanningNatural Language ProcessingAutomated Plan VerificationBenchmark DatasetGym EnvironmentsAgentic FrameworkIterative Refinement
Authors
Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler
Abstract
LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead translate natural language into the Planning Domain Definition Language (PDDL), allowing symbolic planners to produce verifiable plans. However, existing methods frequently rely on rigid generation pipelines, a partial PDDL definition, or human feedback. Furthermore, their evaluation is hindered by the lack of standardized benchmarks with automated verification. To address these limitations, we present PDDLCoder, an agentic framework for PDDL generation from natural language that iteratively generates, analyzes, and refines planning specifications. We further introduce NL-pddlgym, a benchmark dataset comprising 711 planning problems across 23 domains with executable gym environments for the automated verification of plan applicability. Experiments on the NL-pddlgym test set containing 106 problems across 4 held-out domains show that PDDLCoder generates applicable plans for 89.6\% of tested planning problems. This improves upon our adaptations of previous PDDL generation methods, which achieved up to 45.3\%, and outperforms direct LLM planning approaches, which reached up to 74.5\% on the same test set. Our work demonstrates the effectiveness of agentic PDDL generation for planning and establishes a reproducible benchmark for future research on LLM-assisted symbolic planning.