{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PFJF2ZK66AG2MFSZFPVRFXVKTF","short_pith_number":"pith:PFJF2ZK6","schema_version":"1.0","canonical_sha256":"79525d655ef00da616592beb12deaa994ab451653f145c47967754a0c28b8068","source":{"kind":"arxiv","id":"2201.07207","version":2},"attestation_state":"computed","paper":{"title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Deepak Pathak, Igor Mordatch, Pieter Abbeel, Wenlong Huang","submitted_at":"2022-01-18T18:59:45Z","abstract_excerpt":"Can world knowledge learned by large language models (LLMs) be used to act in interactive environments? In this paper, we investigate the possibility of grounding high-level tasks, expressed in natural language (e.g. \"make breakfast\"), to a chosen set of actionable steps (e.g. \"open fridge\"). While prior work focused on learning from explicit step-by-step examples of how to act, we surprisingly find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into mid-level plans without any further training. However, the plans produced n"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.07207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-18T18:59:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"424ca5c5e4e4985e44e2bfb563ca5537bb59aa2e072f10b8c3345179c091f414","abstract_canon_sha256":"7917154177a0061c32ace1ec8841e4647379a9d5679752c1ffeb2f535ac8513d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:40.697798Z","signature_b64":"QNZBA1E2sNY/YVKhlWmCBoFkztGoAbaO/ayGLKDnxruLWL4yIbsUmhq6fW/BdicOx+uRBqMltJsrtx2X63m5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79525d655ef00da616592beb12deaa994ab451653f145c47967754a0c28b8068","last_reissued_at":"2026-07-05T04:02:40.697322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:40.697322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Deepak Pathak, Igor Mordatch, Pieter Abbeel, Wenlong Huang","submitted_at":"2022-01-18T18:59:45Z","abstract_excerpt":"Can world knowledge learned by large language models (LLMs) be used to act in interactive environments? In this paper, we investigate the possibility of grounding high-level tasks, expressed in natural language (e.g. \"make breakfast\"), to a chosen set of actionable steps (e.g. \"open fridge\"). While prior work focused on learning from explicit step-by-step examples of how to act, we surprisingly find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into mid-level plans without any further training. However, the plans produced n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07207","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.07207/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2201.07207","created_at":"2026-07-05T04:02:40.697380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07207v2","created_at":"2026-07-05T04:02:40.697380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07207","created_at":"2026-07-05T04:02:40.697380+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFJF2ZK66AG2","created_at":"2026-07-05T04:02:40.697380+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFJF2ZK66AG2MFSZ","created_at":"2026-07-05T04:02:40.697380+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFJF2ZK6","created_at":"2026-07-05T04:02:40.697380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08024","citing_title":"APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22610","citing_title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18519","citing_title":"As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06673","citing_title":"Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00673","citing_title":"Path Planning in Physically Viable World Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28566","citing_title":"Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06745","citing_title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16932","citing_title":"MORN: Metacognitive Object-Goal Regulation for Resource-Rational Long-Horizon Navigation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20911","citing_title":"FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2209.11302","citing_title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2209.07753","citing_title":"Code as Policies: Language Model Programs for Embodied Control","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17760","citing_title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2205.06175","citing_title":"A Generalist Agent","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2410.02644","citing_title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05846","citing_title":"LoopTrap: Termination Poisoning Attacks on LLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2206.07682","citing_title":"Emergent Abilities of Large Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF","json":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF.json","graph_json":"https://pith.science/api/pith-number/PFJF2ZK66AG2MFSZFPVRFXVKTF/graph.json","events_json":"https://pith.science/api/pith-number/PFJF2ZK66AG2MFSZFPVRFXVKTF/events.json","paper":"https://pith.science/paper/PFJF2ZK6"},"agent_actions":{"view_html":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF","download_json":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF.json","view_paper":"https://pith.science/paper/PFJF2ZK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07207&json=true","fetch_graph":"https://pith.science/api/pith-number/PFJF2ZK66AG2MFSZFPVRFXVKTF/graph.json","fetch_events":"https://pith.science/api/pith-number/PFJF2ZK66AG2MFSZFPVRFXVKTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF/action/storage_attestation","attest_author":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF/action/author_attestation","sign_citation":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF/action/citation_signature","submit_replication":"https://pith.science/pith/PFJF2ZK66AG2MFSZFPVRFXVKTF/action/replication_record"}},"created_at":"2026-07-05T04:02:40.697380+00:00","updated_at":"2026-07-05T04:02:40.697380+00:00"}