Pith Number

pith:5KVYLXRW

pith:2023:5KVYLXRWGJ4WBAR3XOPS4JYP4I

not attested not anchored not stored refs resolved

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

Bo Liu, Joydeep Biswas, Peter Stone, Qiang Liu, Shiqi Zhang, Xiaohan Zhang, Yuqian Jiang

LLM+P lets language models generate optimal plans by routing problems through classical planners via PDDL translation.

arxiv:2304.11477 v3 · 2023-04-22 · cs.AI · cs.RO

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5KVYLXRWGJ4WBAR3XOPS4JYP4I}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

LLM+P is able to provide optimal solutions for most problems, while LLMs fail to provide even feasible plans for most problems.

C2weakest assumption

The assumption that large language models can reliably and accurately translate natural language planning problems into syntactically and semantically correct PDDL without introducing errors that invalidate the planner's output.

C3one line summary

LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.

References

68 extracted · 68 resolved · 17 Pith anchors

[1] Eliza—a computer program for the study of natural language communication between man and machine, 1966

[2] Gpt-4 technical report 2023

[3] Chatgpt for robotics: Design principles and model abilities, 2023

[4] arXiv preprint arXiv:2301.06627 , volume= 2023

[5] Mixout: Effective regularization to finetune large-scale pretrained language models.arXiv preprint arXiv:1909.11299, 1909

Cited by

43 papers in Pith

A Survey on Vision-Language-Action Models for Embodied AI

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Iterative Formalization and Planning in Partially Observable Environments

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis

Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning

Receipt and verification

First computed	2026-05-17T23:39:22.178565Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eaab85de36327960823bbb9f2e270fe21aa4ecdaff875be7c59c4462c3926140

Aliases

arxiv: 2304.11477 · arxiv_version: 2304.11477v3 · doi: 10.48550/arxiv.2304.11477 · pith_short_12: 5KVYLXRWGJ4W · pith_short_16: 5KVYLXRWGJ4WBAR3 · pith_short_8: 5KVYLXRW

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: eaab85de36327960823bbb9f2e270fe21aa4ecdaff875be7c59c4462c3926140

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "396a1a565f7a700875f576367e2f5d97cc41a4f6bf5dbd383f377dad64e1d25c",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-04-22T20:34:03Z",
    "title_canon_sha256": "4b56853ca1c5586d3380a66636ca7dceface5693f2047ea9cd05b1461ce3c5a0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2304.11477",
    "kind": "arxiv",
    "version": 3
  }
}