{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I62ZPU4KQYYRUN6V32AXFAWQA6","short_pith_number":"pith:I62ZPU4K","schema_version":"1.0","canonical_sha256":"47b597d38a86311a37d5de817282d007bc9fa16c7dd855ee9382d36916c1353c","source":{"kind":"arxiv","id":"2209.11302","version":1},"attestation_state":"computed","paper":{"title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Structuring LLM prompts as executable programs lets robots generate valid task plans across any environment and capabilities.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Ankit Goyal, Arsalan Mousavian, Danfei Xu, Dieter Fox, Ishika Singh, Jesse Thomason, Jonathan Tremblay, Valts Blukis","submitted_at":"2022-09-22T20:29:49Z","abstract_excerpt":"Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that ena"},"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":"2209.11302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-22T20:29:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"00e7c202978b484a0722730fa304d289f75814a81f0b7ccc7d0575915e88902c","abstract_canon_sha256":"b022bf70898e2f3bc92f086f14a67b428dfa412c24c0941ede13f1fb6c7b8553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.145750Z","signature_b64":"Vz2Nk3uNKIytKqcTYiLQK7vSnyBxCSsUgCY3YpqYxV1P3nUm19icuZH1RzNgxOxKSh6UrlA84LTTdSEYqJOjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47b597d38a86311a37d5de817282d007bc9fa16c7dd855ee9382d36916c1353c","last_reissued_at":"2026-05-17T23:38:15.145015Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.145015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Structuring LLM prompts as executable programs lets robots generate valid task plans across any environment and capabilities.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Ankit Goyal, Arsalan Mousavian, Danfei Xu, Dieter Fox, Ishika Singh, Jesse Thomason, Jonathan Tremblay, Valts Blukis","submitted_at":"2022-09-22T20:29:49Z","abstract_excerpt":"Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that ena"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That prompting the LLM with program-like specifications of available actions and objects plus example programs will reliably prevent generation of actions impossible in the robot's current context.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ProgPrompt generates situated robot task plans by prompting LLMs with program-like specifications of actions, objects, and executable examples, achieving state-of-the-art success in VirtualHome tasks and physical robot deployment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Structuring LLM prompts as executable programs lets robots generate valid task plans across any environment and capabilities.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"893def829a51ccc9dc07c253a26d7e08007028a5a112edcf626a9194dc1d8a4e"},"source":{"id":"2209.11302","kind":"arxiv","version":1},"verdict":{"id":"f5736e4c-28c7-4432-a50d-33bf13414d78","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T04:17:03.442673Z","strongest_claim":"We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks.","one_line_summary":"ProgPrompt generates situated robot task plans by prompting LLMs with program-like specifications of actions, objects, and executable examples, achieving state-of-the-art success in VirtualHome tasks and physical robot deployment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That prompting the LLM with program-like specifications of available actions and objects plus example programs will reliably prevent generation of actions impossible in the robot's current context.","pith_extraction_headline":"Structuring LLM prompts as executable programs lets robots generate valid task plans across any environment and capabilities."},"references":{"count":39,"sample":[{"doi":"","year":2022,"title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","work_id":"f6e5e4a1-e34b-4602-a7ad-df0c6103a4d0","ref_index":1,"cited_arxiv_id":"2207.05608","is_internal_anchor":true},{"doi":"","year":2022,"title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","work_id":"e2e590a8-7af9-4ab9-b5be-29c703ef90fb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Socratic models: Composing zero-shot multimodal reasoning with language,","work_id":"e4f96497-1902-4687-96c8-4dbaab9bc4e2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Do as i can, not as i say: Grounding language in robotic affordances,","work_id":"fe688c6a-e96c-48e7-89b6-b38c4aa20332","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1971,"title":"Strips: A new approach to the application of theorem proving to problem solving,","work_id":"dbef61d6-f55d-4d66-bfe9-c65ef4e4c6ea","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"04ae6d6566cd57f6349f397821a250519267993b104ea0e58c62483d02054434","internal_anchors":1},"formal_canon":{"evidence_count":1,"snapshot_sha256":"8763581bdedf7ee1586a2adaf20373c6629b6ec307bdb4d08ed751c2d1f80c88"},"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":"2209.11302","created_at":"2026-05-17T23:38:15.145137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11302v1","created_at":"2026-05-17T23:38:15.145137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11302","created_at":"2026-05-17T23:38:15.145137+00:00"},{"alias_kind":"pith_short_12","alias_value":"I62ZPU4KQYYR","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"I62ZPU4KQYYRUN6V","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"I62ZPU4K","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":21,"sample":[{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":32,"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":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19587","citing_title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":147,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10605","citing_title":"LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator","ref_index":9,"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":100,"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":44,"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":22,"is_internal_anchor":true},{"citing_arxiv_id":"2603.08388","citing_title":"A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2304.11477","citing_title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":59,"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":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08224","citing_title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07395","citing_title":"A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18463","citing_title":"Using large language models for embodied planning introduces systematic safety risks","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17807","citing_title":"Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6","json":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6.json","graph_json":"https://pith.science/api/pith-number/I62ZPU4KQYYRUN6V32AXFAWQA6/graph.json","events_json":"https://pith.science/api/pith-number/I62ZPU4KQYYRUN6V32AXFAWQA6/events.json","paper":"https://pith.science/paper/I62ZPU4K"},"agent_actions":{"view_html":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6","download_json":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6.json","view_paper":"https://pith.science/paper/I62ZPU4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11302&json=true","fetch_graph":"https://pith.science/api/pith-number/I62ZPU4KQYYRUN6V32AXFAWQA6/graph.json","fetch_events":"https://pith.science/api/pith-number/I62ZPU4KQYYRUN6V32AXFAWQA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6/action/storage_attestation","attest_author":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6/action/author_attestation","sign_citation":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6/action/citation_signature","submit_replication":"https://pith.science/pith/I62ZPU4KQYYRUN6V32AXFAWQA6/action/replication_record"}},"created_at":"2026-05-17T23:38:15.145137+00:00","updated_at":"2026-05-17T23:38:15.145137+00:00"}