{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YKPOPSNE6HBDMPES2DFWZJM6GA","short_pith_number":"pith:YKPOPSNE","schema_version":"1.0","canonical_sha256":"c29ee7c9a4f1c2363c92d0cb6ca59e303132e4a2aba2fa7d8a741cda0b0b8f7e","source":{"kind":"arxiv","id":"2506.09171","version":2},"attestation_state":"computed","paper":{"title":"Fact-Augmented Lookahead Planning for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Max Ruiz Luyten, Mihaela van der Schaar, Samuel Holt, Thomas Pouplin","submitted_at":"2025-06-10T18:36:31Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient. We introduce LWM-Planner, a fact-augmented lookahead planning framework that improves agent behavior purely through in-context learning. After each episode, the agent extracts task-critical atomic facts from its trajectories, validates candidates with a lightweight predictive-consistency filter (and optionally compresses them), and uses the resulting fact set to conditi"},"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":"2506.09171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T18:36:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c72f93fc15607f402f414abb4be0e5ac6126c9e832153d6ac9b17710a79ac069","abstract_canon_sha256":"6c0e8c128c0b972d9c6ba2f42993c02b4f6a572b9a2db7266cd3be40c44b265e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:28.237406Z","signature_b64":"qBoncETjnEs19j3tsoidIhRWoVN6VrCieBKe+LjolY9VPB9ZjHSx2g8okKChCZ7b+0+j/daimF0Xhs0rQld0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c29ee7c9a4f1c2363c92d0cb6ca59e303132e4a2aba2fa7d8a741cda0b0b8f7e","last_reissued_at":"2026-06-10T01:08:28.236215Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:28.236215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fact-Augmented Lookahead Planning for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Max Ruiz Luyten, Mihaela van der Schaar, Samuel Holt, Thomas Pouplin","submitted_at":"2025-06-10T18:36:31Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient. We introduce LWM-Planner, a fact-augmented lookahead planning framework that improves agent behavior purely through in-context learning. After each episode, the agent extracts task-critical atomic facts from its trajectories, validates candidates with a lightweight predictive-consistency filter (and optionally compresses them), and uses the resulting fact set to conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09171","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/2506.09171/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":"2506.09171","created_at":"2026-06-10T01:08:28.236385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09171v2","created_at":"2026-06-10T01:08:28.236385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09171","created_at":"2026-06-10T01:08:28.236385+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKPOPSNE6HBD","created_at":"2026-06-10T01:08:28.236385+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKPOPSNE6HBDMPES","created_at":"2026-06-10T01:08:28.236385+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKPOPSNE","created_at":"2026-06-10T01:08:28.236385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA","json":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA.json","graph_json":"https://pith.science/api/pith-number/YKPOPSNE6HBDMPES2DFWZJM6GA/graph.json","events_json":"https://pith.science/api/pith-number/YKPOPSNE6HBDMPES2DFWZJM6GA/events.json","paper":"https://pith.science/paper/YKPOPSNE"},"agent_actions":{"view_html":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA","download_json":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA.json","view_paper":"https://pith.science/paper/YKPOPSNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09171&json=true","fetch_graph":"https://pith.science/api/pith-number/YKPOPSNE6HBDMPES2DFWZJM6GA/graph.json","fetch_events":"https://pith.science/api/pith-number/YKPOPSNE6HBDMPES2DFWZJM6GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA/action/storage_attestation","attest_author":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA/action/author_attestation","sign_citation":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA/action/citation_signature","submit_replication":"https://pith.science/pith/YKPOPSNE6HBDMPES2DFWZJM6GA/action/replication_record"}},"created_at":"2026-06-10T01:08:28.236385+00:00","updated_at":"2026-06-10T01:08:28.236385+00:00"}