{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KVYLXRWGJ4WBAR3XOPS4JYP4I","short_pith_number":"pith:5KVYLXRW","schema_version":"1.0","canonical_sha256":"eaab85de36327960823bbb9f2e270fe21aa4ecdaff875be7c59c4462c3926140","source":{"kind":"arxiv","id":"2304.11477","version":3},"attestation_state":"computed","paper":{"title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM+P lets language models generate optimal plans by routing problems through classical planners via PDDL translation.","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bo Liu, Joydeep Biswas, Peter Stone, Qiang Liu, Shiqi Zhang, Xiaohan Zhang, Yuqian Jiang","submitted_at":"2023-04-22T20:34:03Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizon planning problems. By contrast, classical planners, once a problem is given in a formatted way, can use efficient search algorithms to quickly identify correct, or even optimal, plans. In an effort to get the best of both worlds, this paper introduces LLM+P, the first framework that incorporates the strengths of classical planners into LLMs"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.11477","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-22T20:34:03Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4b56853ca1c5586d3380a66636ca7dceface5693f2047ea9cd05b1461ce3c5a0","abstract_canon_sha256":"396a1a565f7a700875f576367e2f5d97cc41a4f6bf5dbd383f377dad64e1d25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:22.179267Z","signature_b64":"rNM7o2/pGFAarKvchGJdcfE9ARnA4/6yc4iBGXZ0/Vkiy+WN3HQI7YVGTHqU0T3MRB5gn/+hqYlB8QWL/SOxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaab85de36327960823bbb9f2e270fe21aa4ecdaff875be7c59c4462c3926140","last_reissued_at":"2026-05-17T23:39:22.178565Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:22.178565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM+P lets language models generate optimal plans by routing problems through classical planners via PDDL translation.","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bo Liu, Joydeep Biswas, Peter Stone, Qiang Liu, Shiqi Zhang, Xiaohan Zhang, Yuqian Jiang","submitted_at":"2023-04-22T20:34:03Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizon planning problems. By contrast, classical planners, once a problem is given in a formatted way, can use efficient search algorithms to quickly identify correct, or even optimal, plans. In an effort to get the best of both worlds, this paper introduces LLM+P, the first framework that incorporates the strengths of classical planners into LLMs"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LLM+P is able to provide optimal solutions for most problems, while LLMs fail to provide even feasible plans for most problems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM+P lets language models generate optimal plans by routing problems through classical planners via PDDL translation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dcbd98632e4f006e1f663741ecd0f24fd27e19b96485ba09bc11516271ec2c54"},"source":{"id":"2304.11477","kind":"arxiv","version":3},"verdict":{"id":"aa3bb118-bf73-4db8-8031-2d087bac6c9e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:30:44.381182Z","strongest_claim":"LLM+P is able to provide optimal solutions for most problems, while LLMs fail to provide even feasible plans for most problems.","one_line_summary":"LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.","pipeline_version":"pith-pipeline@v0.9.0","weakest_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.","pith_extraction_headline":"LLM+P lets language models generate optimal plans by routing problems through classical planners via PDDL translation."},"references":{"count":68,"sample":[{"doi":"","year":1966,"title":"Eliza—a computer program for the study of natural language communication between man and machine,","work_id":"e968b6f0-dc67-4ba3-bbee-78c2dd5a50f5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Gpt-4 technical report","work_id":"195de85d-887e-420c-ba80-6443af256f61","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Chatgpt for robotics: Design principles and model abilities,","work_id":"5597eeb9-de68-43cb-a3df-a346ec30197c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2301.06627 , volume=","work_id":"9b09d8dc-9d65-4791-a90a-a6f71e2374d0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1909,"title":"Mixout: Effective regularization to finetune large-scale pretrained language models.arXiv preprint arXiv:1909.11299,","work_id":"16f75ae4-57ac-4285-a1ac-30c476fdfe71","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":68,"snapshot_sha256":"042e8486c61237d46a7d6fce10ca3989a4e02132ffdddc79d42bf3196964a5c9","internal_anchors":17},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.11477","created_at":"2026-05-17T23:39:22.178673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11477v3","created_at":"2026-05-17T23:39:22.178673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11477","created_at":"2026-05-17T23:39:22.178673+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KVYLXRWGJ4W","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KVYLXRWGJ4WBAR3","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KVYLXRW","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":43,"internal_anchor_count":43,"sample":[{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":219,"is_internal_anchor":true},{"citing_arxiv_id":"2505.13126","citing_title":"Iterative Formalization and Planning in Partially Observable Environments","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15975","citing_title":"Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16142","citing_title":"Property-Guided LLM Program Synthesis for Planning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":124,"is_internal_anchor":true},{"citing_arxiv_id":"2506.04500","citing_title":"\"Don't Do That!\": Guiding Embodied Systems through Large Language Model-based Constraint Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21545","citing_title":"UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00432","citing_title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08150","citing_title":"Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2509.16615","citing_title":"LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14063","citing_title":"Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":251,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09629","citing_title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2309.02427","citing_title":"Cognitive Architectures for Language Agents","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2305.04091","citing_title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04129","citing_title":"KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2410.05229","citing_title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2402.02716","citing_title":"Understanding the planning of LLM agents: A survey","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I","json":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I.json","graph_json":"https://pith.science/api/pith-number/5KVYLXRWGJ4WBAR3XOPS4JYP4I/graph.json","events_json":"https://pith.science/api/pith-number/5KVYLXRWGJ4WBAR3XOPS4JYP4I/events.json","paper":"https://pith.science/paper/5KVYLXRW"},"agent_actions":{"view_html":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I","download_json":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I.json","view_paper":"https://pith.science/paper/5KVYLXRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11477&json=true","fetch_graph":"https://pith.science/api/pith-number/5KVYLXRWGJ4WBAR3XOPS4JYP4I/graph.json","fetch_events":"https://pith.science/api/pith-number/5KVYLXRWGJ4WBAR3XOPS4JYP4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I/action/storage_attestation","attest_author":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I/action/author_attestation","sign_citation":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I/action/citation_signature","submit_replication":"https://pith.science/pith/5KVYLXRWGJ4WBAR3XOPS4JYP4I/action/replication_record"}},"created_at":"2026-05-17T23:39:22.178673+00:00","updated_at":"2026-05-17T23:39:22.178673+00:00"}