{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WTB4XYYZU6OKHGSFJTRP5PODD2","short_pith_number":"pith:WTB4XYYZ","schema_version":"1.0","canonical_sha256":"b4c3cbe319a79ca39a454ce2febdc31eb538734577ae4c4fb5971639d80d1925","source":{"kind":"arxiv","id":"2209.07753","version":4},"attestation_state":"computed","paper":{"title":"Code as Policies: Language Model Programs for Embodied Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Language models write executable robot policies by composing code from a few example commands.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Brian Ichter, Fei Xia, Jacky Liang, Karol Hausman, Peng Xu, Pete Florence, Wenlong Huang","submitted_at":"2022-09-16T07:17:23Z","abstract_excerpt":"Large language models (LLMs) trained on code completion have been shown to be capable of synthesizing simple Python programs from docstrings [1]. We find that these code-writing LLMs can be re-purposed to write robot policy code, given natural language commands. Specifically, policy code can express functions or feedback loops that process perception outputs (e.g.,from object detectors [2], [3]) and parameterize control primitive APIs. When provided as input several example language commands (formatted as comments) followed by corresponding policy code (via few-shot prompting), LLMs can take i"},"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":true},"canonical_record":{"source":{"id":"2209.07753","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-16T07:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"480718d0058d1c2f38bcafeb7fc1609a083acbe6c53019337a21fb929fa1a8b3","abstract_canon_sha256":"d8ced9d954021ac1db8d3ff885f46eac81e76c8d8f3f3b8123b2e38e4ecce031"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.693186Z","signature_b64":"zre/lXwiz2FOvLd4rqY266N4+IDBvQTKDX2KzqFXKJtDsomlVjqcLxI+syG23mdtFEyl7vSRaJYX43smKwNpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c3cbe319a79ca39a454ce2febdc31eb538734577ae4c4fb5971639d80d1925","last_reissued_at":"2026-05-17T23:39:19.692326Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.692326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code as Policies: Language Model Programs for Embodied Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Language models write executable robot policies by composing code from a few example commands.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Brian Ichter, Fei Xia, Jacky Liang, Karol Hausman, Peng Xu, Pete Florence, Wenlong Huang","submitted_at":"2022-09-16T07:17:23Z","abstract_excerpt":"Large language models (LLMs) trained on code completion have been shown to be capable of synthesizing simple Python programs from docstrings [1]. We find that these code-writing LLMs can be re-purposed to write robot policy code, given natural language commands. Specifically, policy code can express functions or feedback loops that process perception outputs (e.g.,from object detectors [2], [3]) and parameterize control primitive APIs. When provided as input several example language commands (formatted as comments) followed by corresponding policy code (via few-shot prompting), LLMs can take i"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When provided as input several example language commands (formatted as comments) followed by corresponding policy code (via few-shot prompting), LLMs can take in new commands and autonomously re-compose API calls to generate new policy code respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the LLM-generated code will execute correctly and safely on physical robots for novel commands without runtime errors or the need for additional verification layers.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Language models write executable robot policies by composing code from a few example commands.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"470d07b5c414fcdc910d20fc21ada31822fe767ea0215669bcfa733256168e85"},"source":{"id":"2209.07753","kind":"arxiv","version":4},"verdict":{"id":"3e578c85-85a9-4284-a948-e7a23e50242f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:34:09.000934Z","strongest_claim":"When provided as input several example language commands (formatted as comments) followed by corresponding policy code (via few-shot prompting), LLMs can take in new commands and autonomously re-compose API calls to generate new policy code respectively.","one_line_summary":"Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the LLM-generated code will execute correctly and safely on physical robots for novel commands without runtime errors or the need for additional verification layers.","pith_extraction_headline":"Language models write executable robot policies by composing code from a few example commands."},"references":{"count":145,"sample":[{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":1,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2021,"title":"Mdetr-modulated detection for end-to-end multi-modal understanding,","work_id":"6721969f-722b-4bba-99aa-53b14bc21994","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","work_id":"59541f32-18cf-4328-ad60-c9018e1401cf","ref_index":3,"cited_arxiv_id":"2104.13921","is_internal_anchor":true},{"doi":"","year":2020,"title":"Robots that use language,","work_id":"e9899a79-9a17-47bd-9003-ecd3eb28d940","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1971,"title":"Procedures as a representation for data in a computer program for understanding natural language,","work_id":"b0f61573-32b7-4404-b123-c6b18536f5cb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":145,"snapshot_sha256":"80eecb5f69ff894e7f40e112ede521abe3f348cc1bd105dccc5a18daf56cc162","internal_anchors":17},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f403e391445d27071458bb4975fecbb024d680e10c47424b57e36b40760463cb"},"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":"2209.07753","created_at":"2026-05-17T23:39:19.692482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07753v4","created_at":"2026-05-17T23:39:19.692482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07753","created_at":"2026-05-17T23:39:19.692482+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTB4XYYZU6OK","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTB4XYYZU6OKHGSF","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTB4XYYZ","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2602.10085","citing_title":"CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":203,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17321","citing_title":"Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2302.01560","citing_title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2305.17144","citing_title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15956","citing_title":"ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17834","citing_title":"Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":243,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13119","citing_title":"Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11951","citing_title":"From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27699","citing_title":"Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09656","citing_title":"ORICF -- Open Robotics Inference and Control Framework","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09055","citing_title":"Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01477","citing_title":"Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21138","citing_title":"Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems","ref_index":109,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2","json":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2.json","graph_json":"https://pith.science/api/pith-number/WTB4XYYZU6OKHGSFJTRP5PODD2/graph.json","events_json":"https://pith.science/api/pith-number/WTB4XYYZU6OKHGSFJTRP5PODD2/events.json","paper":"https://pith.science/paper/WTB4XYYZ"},"agent_actions":{"view_html":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2","download_json":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2.json","view_paper":"https://pith.science/paper/WTB4XYYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07753&json=true","fetch_graph":"https://pith.science/api/pith-number/WTB4XYYZU6OKHGSFJTRP5PODD2/graph.json","fetch_events":"https://pith.science/api/pith-number/WTB4XYYZU6OKHGSFJTRP5PODD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2/action/storage_attestation","attest_author":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2/action/author_attestation","sign_citation":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2/action/citation_signature","submit_replication":"https://pith.science/pith/WTB4XYYZU6OKHGSFJTRP5PODD2/action/replication_record"}},"created_at":"2026-05-17T23:39:19.692482+00:00","updated_at":"2026-05-17T23:39:19.692482+00:00"}