{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C7BAFTVDEVQCA3MT62FQPTP5IU","short_pith_number":"pith:C7BAFTVD","schema_version":"1.0","canonical_sha256":"17c202cea32560206d93f68b07cdfd451b4587b7d8a907dad826b94c387dbf52","source":{"kind":"arxiv","id":"2602.21198","version":3},"attestation_state":"computed","paper":{"title":"Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Embodied LLMs improve long-horizon task performance by reflecting on failures before and after each execution at test time.","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huang Huang, Jiajun Wu, Leonidas Guibas, Li Fei-Fei, Manling Li, Yejin Choi, Yining Hong","submitted_at":"2026-02-24T18:55:18Z","abstract_excerpt":"Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \\textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \\textit{reflection-on-action}, which uses test-time training to update b"},"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":true},"canonical_record":{"source":{"id":"2602.21198","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-24T18:55:18Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"5c27eaf0d8482cbb5b9a33d01ba2228571b72860dcd92b60b31d246ffc847fdb","abstract_canon_sha256":"25f2e722250a220f2d4d04f790431684a0c0f84d49d3875744f254df9b6129d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:07.074418Z","signature_b64":"L/oihxwPgdj5TgODlnzeZC6KhEt8XazKwhN+0dicO3LdUz9okEfIttgIWfR1+d0WgzeaMOCqaSnfat6PVguOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c202cea32560206d93f68b07cdfd451b4587b7d8a907dad826b94c387dbf52","last_reissued_at":"2026-05-26T02:04:07.073593Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:07.073593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Embodied LLMs improve long-horizon task performance by reflecting on failures before and after each execution at test time.","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huang Huang, Jiajun Wu, Leonidas Guibas, Li Fei-Fei, Manling Li, Yejin Choi, Yining Hong","submitted_at":"2026-02-24T18:55:18Z","abstract_excerpt":"Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \\textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \\textit{reflection-on-action}, which uses test-time training to update b"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That internal model reflections and external feedback after execution can reliably identify the causes of failures and that test-time training updates can improve the policy without instability or loss of prior capabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reflective Test-Time Planning combines pre-execution internal reflection with post-execution model updates to improve embodied LLMs on household and manipulation tasks with better long-horizon credit assignment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Embodied LLMs improve long-horizon task performance by reflecting on failures before and after each execution at test time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6aeef0b29f34d89eca50c8277f822abc0fecc255f08d3a7ee00447d702b814fe"},"source":{"id":"2602.21198","kind":"arxiv","version":3},"verdict":{"id":"76727724-db0d-4b3e-a149-bf9ab9226bd3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:41:10.555564Z","strongest_claim":"Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead.","one_line_summary":"Reflective Test-Time Planning combines pre-execution internal reflection with post-execution model updates to improve embodied LLMs on household and manipulation tasks with better long-horizon credit assignment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That internal model reflections and external feedback after execution can reliably identify the causes of failures and that test-time training updates can improve the policy without instability or loss of prior capabilities.","pith_extraction_headline":"Embodied LLMs improve long-horizon task performance by reflecting on failures before and after each execution at test time."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.21198/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":2,"snapshot_sha256":"122c40ea650ad326a3f0460910b38b598ec58449d188a4df0cb8e6f99d1b497a"},"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":"2602.21198","created_at":"2026-05-26T02:04:07.073721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.21198v3","created_at":"2026-05-26T02:04:07.073721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21198","created_at":"2026-05-26T02:04:07.073721+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7BAFTVDEVQC","created_at":"2026-05-26T02:04:07.073721+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7BAFTVDEVQCA3MT","created_at":"2026-05-26T02:04:07.073721+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7BAFTVD","created_at":"2026-05-26T02:04:07.073721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":141,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU","json":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU.json","graph_json":"https://pith.science/api/pith-number/C7BAFTVDEVQCA3MT62FQPTP5IU/graph.json","events_json":"https://pith.science/api/pith-number/C7BAFTVDEVQCA3MT62FQPTP5IU/events.json","paper":"https://pith.science/paper/C7BAFTVD"},"agent_actions":{"view_html":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU","download_json":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU.json","view_paper":"https://pith.science/paper/C7BAFTVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.21198&json=true","fetch_graph":"https://pith.science/api/pith-number/C7BAFTVDEVQCA3MT62FQPTP5IU/graph.json","fetch_events":"https://pith.science/api/pith-number/C7BAFTVDEVQCA3MT62FQPTP5IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU/action/storage_attestation","attest_author":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU/action/author_attestation","sign_citation":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU/action/citation_signature","submit_replication":"https://pith.science/pith/C7BAFTVDEVQCA3MT62FQPTP5IU/action/replication_record"}},"created_at":"2026-05-26T02:04:07.073721+00:00","updated_at":"2026-05-26T02:04:07.073721+00:00"}