Compiling Temporal Numeric Planning into Discrete PDDL+: Extended Version

Andrea Micheli; Enrico Scala; Alessandro Valentini

cs.AIMar 12, 2026

Compiling Temporal Numeric Planning into Discrete PDDL+: Extended Version

Authors: Andrea Micheli, Enrico Scala, Alessandro Valentini

Organizations: Fondazione Bruno Kessler, Trento, Italy · University of Brescia, Italy

Abstract

Since the introduction of the PDDL+ modeling language, it was known that temporal planning with durative actions (as in PDDL 2.1) could be compiled into PDDL+. However, no practical compilation was presented in the literature ever since. We present a practical compilation from temporal planning with durative actions into PDDL+, fully capturing the semantics and only assuming the non-self-overlapping of actions. Our compilation is polynomial, retains the plan length up to a constant factor and is experimentally shown to be of practical relevance for hard temporal numeric problems.

Figures & tables

Domain	ENHSP	ENHSP	ARIES	OPTIC	TAMER	TFLAP	Next-	Patty
	LG	WA					FLAP
MatchCellar	7	12	20	9	7	20	2	4
MaJSP	20	19	18	N/A	20	N/A	N/A	N/A
T-Plant-Wat	20	16	15	20	12	0	0	13
T-Sailing	11	20	6	7	3	2	7	2
Total (80)	58	67	59	36	42	22	9	19

Table 1: Coverage analysis domain by domain, planner by planner. Bold for best, N/A for Not Applicable.

Figure 1: Cactus (survival) plot (left) and run-time scatter plot for the planners with highest coverage (right).

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
Aug 17, 2026Veit Laule, Jiangtao Shuai, Manfred Hauswirth +1LLM Planning Symbolic Planning
Technical University of Berlin Berlin, Germany · Fraunhofer FOKUS & Technical University of Berlin Berlin, Germany
RAMP: Hybrid DRL for Online Learning of Numeric Action Models
Apr 9, 2026Yarin Benyamin, Argaman Mordoch, Shahaf S. Shperberg +1Model-Based RL Model-Based Planning
Ben-Gurion University of the Negev, Be’er Sheva, Israel
GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
Mar 10, 2026Andrew Murray, Danial Dervovic, Alberto Pozanco +1Symbolic Planning LLM-Based Program Synthesis
J.P. Morgan AI Research

Aug 17, 2026J/K move · Enter open · S save

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler

Technical University of Berlin Berlin, Germany · Fraunhofer FOKUS & Technical University of Berlin Berlin, Germany

LLM Planning Symbolic Planning LLM Agent Planning

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

RAMP: Hybrid DRL for Online Learning of Numeric Action Models

GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models