pddl

Tag

Cards List
#pddl

LLM-Only PDDL Domain Repair with Open-Weight Models

arXiv cs.AI · yesterday Cached

This paper evaluates open-weight large language models for PDDL domain repair in AI planning, showing they outperform symbolic baselines but struggle with reliable test constraint satisfaction.

0 favorites 0 likes
#pddl

A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems

arXiv cs.AI · 2026-06-15 Cached

This paper proposes a temporal planning framework for dynamic route optimization and disruption management in heterogeneous multi-gauge railway systems. It formulates railway operations as a temporal planning problem using PDDL 2.1, generates conflict-free timestamped operational plans, and reduces reliance on manual decision-making, evaluated on benchmark problems with up to 1,000 track points and 120 trains.

0 favorites 0 likes
#pddl

Property-Guided LLM Program Synthesis for Planning

arXiv cs.AI · 2026-05-18 Cached

This paper proposes property-guided LLM program synthesis, using counterexample-guided inductive synthesis (CEGIS) to provide concrete feedback when a candidate program fails a formal property, reducing the number of generations and evaluation costs. Applied to PDDL planning domains for synthesizing direct heuristic functions, the method outperforms prior approaches, generating seven times fewer programs and solving more tasks without search.

0 favorites 0 likes
#pddl

Zero-Shot Goal Recognition with Large Language Models

arXiv cs.AI · 2026-05-18 Cached

This paper presents the first systematic zero-shot evaluation of frontier large language models as goal recognizers on classical PDDL planning benchmarks, finding that some models scale with evidence while others rely on world-knowledge priors regardless of observation accumulation.

0 favorites 0 likes
#pddl

Differentiable Learning of Lifted Action Schemas for Classical Planning

arXiv cs.AI · 2026-05-14 Cached

This paper introduces a neural network architecture that learns lifted action schemas from fully observed state traces with unobserved action arguments, aiming to enable robust learning of planning domains for neuro-symbolic models.

0 favorites 0 likes
← Back to home

Submit Feedback