SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.11014 · 2023

Generalized Planning in PDDL Domains with Pretrained Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.11014.json · badge: /api/ran/2305.11014.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
tomsilver/llm-genplan canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_pddl_from_url Ran
ran on a synthesized input
tomsilver/llm-genplan/llm_genplan/utils.py
code served (permissive licence) · get_code("c5fd03dcaacfcd94")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
from pathlib import Path
import os

# Create a temporary directory to use as cache_dir
temp_dir = tempfile.mkdtemp()
cache_dir = Path(temp_dir)

# Create a simple valid PDDL file content
valid_pddl_content = """(define (domain test-domain)
  (:requirements :strips :typing)
  (:types location object)
  (:init)
  (:action move
    :parameters (?from ?to - location)
    :precondition (at ?from)
    :effect (and (at ?to) (not (at ?from)))
  )
)"""

# Pre-populate cache with a valid PDDL file
sanitized_url = ''.join((x for x in "http://example.com/test.pddl" if x.isalnum()))
file_name = f'cached-pddl-{sanitized_url}'
file_path = cache_dir / file_name
with open(file_path, 'w', encoding='utf-8') as f:
    f.write(valid_pddl_content)

ARGS = {
    'url': 'http://example.com/test.pddl',
    'cache_dir': cache_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
set_to_reproducible_str Not yet run
unverified (harvested, no recorded run)
tomsilver/llm-genplan/llm_genplan/utils.py
code served (permissive licence) · get_code("2a3e3db1f7a9ca22")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.11014")
get_code_for_paper("2305.11014")
have("2305.11014")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.11014.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.11014.svg)](https://syntology.ai/paper/2305.11014)

Connect an agent — have() is free.