Publikation
LODGE: Joint Hierarchical Task Planning and Learning of Domain Models with Grounded Execution
Claudius Kienle; Benjamin Alt; Oleg Arenz; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2505.13497, Pages 1-20, arXiv, 2025.
Zusammenfassung
Large Language Models ( LLMs) enable planning from natural language instruc-
tions using implicit world knowledge, but often produce flawed plans that require
refinement. Instead of directly predicting plans, recent methods aim to learn a
problem domain that can be solved for different goal states using classical planners.
However, these approaches require significant human feedback to obtain useful
models. We address this shortcoming by learning hierarchical domains, where low-
level predicates and actions are composed into higher-level counterparts, and by
leveraging simulation to validate their preconditions and effects. This hierarchical
approach is particularly powerful for long-horizon planning, where LLM-based
planning approaches typically struggle. Furthermore, we introduce a central error
reasoner to ensure consistency among the different planning levels. Evaluation
on two challenging International Planning Competition (IPC ) domains and a long-
horizon robot manipulation task demonstrates higher planning success rates than
state-of-the-art domain synthesis and LLM-modulo planning methods, while con-
structing high-quality models of the domain. Resources, videos and detailed exper-
iment results are available at https://claudius-kienle.github.io/lodge.