Pith. sign in

REVIEW 5 cited by

Generalized Planning in PDDL Domains with Pretrained Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.11014 v2 pith:Z6K35CSD submitted 2023-05-18 cs.AI

classification cs.AI
keywords tasksdomaindomainsfourgeneralizedgpt-4pddlprogram
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly

    cs.CL 2025-06 conditional novelty 7.0 of 10

    LIRAS synthesizes PDDL world models and agent configurations from language, parses video frames into symbolic states, and runs Bayesian inverse planning (SIAM) to produce human-like graded social inferences across fiv...

  2. Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning

    cs.RO 2026-07 conditional novelty 6.5 of 10

    HUME lets robots generate, plan over, and actively verify object-centric hypotheses from foundation models so incomplete symbolic models become usable for open-world household tasks.

  3. A Solver-Aided Hierarchical Language for LLM-Driven CAD Design

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A solver-aided hierarchical DSL lets an untuned LLM generate precise, editable 2D CAD geometry from text prompts, outperforming OpenSCAD slightly on CLIP alignment.

  4. Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following

    cs.AI 2024-12 conditional novelty 6.0 of 10

    A few-shot LLM planner for ALFRED that relabels suboptimal trajectories with hindsight prompts reaches 25.51 SR on Test Seen, approaching or beating the full-shot HLSM baseline.

  5. Scaling Laws for State Dynamics in Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    LLM next-state prediction accuracy degrades with larger state spaces and sparser transitions, with state tracking distributed across several attention heads.

Pith tools