{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-the-limit-of-language-models-as-planning","title":"On the Limit of Language Models as Planning Formalizers","arxiv_id":"2412.09879","date":"2024-12-13","proceeding":null,"authors":["Cassie Huang","Li Zhang"],"abstract":"Large Language Models have been shown to fail to create executable and verifiable plans in grounded environments. An emerging line of work shows success in using LLM as a formalizer to generate a formal representation (e.g., PDDL) of the planning domain, which can be deterministically solved to find a plan. We systematically evaluate this methodology while bridging some major gaps. While previous work only generates a partial PDDL representation given templated and thus unrealistic environment descriptions, we generate the complete representation given descriptions of various naturalness levels. Among an array of observations critical to improve LLMs' formal planning ability, we note that large enough models can effectively formalize descriptions as PDDL, outperforming those directly generating plans, while being robust to lexical perturbation. As the descriptions become more natural-sounding, we observe a decrease in performance and provide detailed error analysis.","url_abs":"https://arxiv.org/abs/2412.09879v1","url_pdf":"https://arxiv.org/pdf/2412.09879v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-the-limit-of-language-models-as-planning","repo_url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.09879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09879"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"93c3a1ab472fe9c7","entry":"plan_to_path","repo":"cassiehuang22/llm-as-pddl-formalizer","repo_kind":"official","path":"source/run_val.py","file_url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer/blob/HEAD/source/run_val.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93c3a1ab472fe9c7"}},{"code_sha256_prefix":"9e3beeaef324fadd","entry":"standardize_blocks","repo":"cassiehuang22/llm-as-pddl-formalizer","repo_kind":"official","path":"source/run_val.py","file_url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer/blob/HEAD/source/run_val.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e3beeaef324fadd"}},{"code_sha256_prefix":"9d3a217c48eddfea","entry":"run_formalizer_gpt","repo":"cassiehuang22/llm-as-pddl-formalizer","repo_kind":"official","path":"source/llm-as-formalizer.py","file_url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer/blob/HEAD/source/llm-as-formalizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d3a217c48eddfea"}},{"code_sha256_prefix":"f9954522d9e82e7f","entry":"validate_plan","repo":"cassiehuang22/llm-as-pddl-formalizer","repo_kind":"official","path":"source/run_val.py","file_url":"https://github.com/cassiehuang22/llm-as-pddl-formalizer/blob/HEAD/source/run_val.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9954522d9e82e7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}