{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TVHKZUZWSWA23QQ7DQI3LFMXXZ","short_pith_number":"pith:TVHKZUZW","schema_version":"1.0","canonical_sha256":"9d4eacd3369581adc21f1c11b59597be757d204c9f8ef620c5614877dbcecfba","source":{"kind":"arxiv","id":"2605.28842","version":1},"attestation_state":"computed","paper":{"title":"Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Liu, Yanxuan Yu, Ying Nian Wu","submitted_at":"2026-04-27T08:18:12Z","abstract_excerpt":"The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods often rely on black-box heuristics or gradient-free search, which lack interpretability, generalization, and sample efficiency. In this work, we introduce \\textbf{Thoughts-as-Planning}, a novel framework that formalizes reasoning chain optimization as a sequential decision-making process over a latent semantic space. We model the LLM as a partially observable e"},"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":"2605.28842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-27T08:18:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d60341afbd52b409fbd4cfd23227ff4568f29e51f5132a00c4c2499f287f799a","abstract_canon_sha256":"356b9380f2953d5f3fcf13aee4a33eee2f4daceee28111aa7490f226874d1f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:13.745663Z","signature_b64":"Gr8E+RVd1X5ptru+kZDKj8lXBTGSBvRwtLeZCErmxiLAjbDwR2XBrdoBiHNlHgAzTXP+8YD4o7gfG5xHsP+fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d4eacd3369581adc21f1c11b59597be757d204c9f8ef620c5614877dbcecfba","last_reissued_at":"2026-05-29T00:04:13.744847Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:13.744847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Liu, Yanxuan Yu, Ying Nian Wu","submitted_at":"2026-04-27T08:18:12Z","abstract_excerpt":"The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods often rely on black-box heuristics or gradient-free search, which lack interpretability, generalization, and sample efficiency. In this work, we introduce \\textbf{Thoughts-as-Planning}, a novel framework that formalizes reasoning chain optimization as a sequential decision-making process over a latent semantic space. We model the LLM as a partially observable e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28842","kind":"arxiv","version":1},"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/2605.28842/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":"2605.28842","created_at":"2026-05-29T00:04:13.744943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28842v1","created_at":"2026-05-29T00:04:13.744943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28842","created_at":"2026-05-29T00:04:13.744943+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVHKZUZWSWA2","created_at":"2026-05-29T00:04:13.744943+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVHKZUZWSWA23QQ7","created_at":"2026-05-29T00:04:13.744943+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVHKZUZW","created_at":"2026-05-29T00:04:13.744943+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/TVHKZUZWSWA23QQ7DQI3LFMXXZ","json":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ.json","graph_json":"https://pith.science/api/pith-number/TVHKZUZWSWA23QQ7DQI3LFMXXZ/graph.json","events_json":"https://pith.science/api/pith-number/TVHKZUZWSWA23QQ7DQI3LFMXXZ/events.json","paper":"https://pith.science/paper/TVHKZUZW"},"agent_actions":{"view_html":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ","download_json":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ.json","view_paper":"https://pith.science/paper/TVHKZUZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28842&json=true","fetch_graph":"https://pith.science/api/pith-number/TVHKZUZWSWA23QQ7DQI3LFMXXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TVHKZUZWSWA23QQ7DQI3LFMXXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ/action/storage_attestation","attest_author":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ/action/author_attestation","sign_citation":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ/action/citation_signature","submit_replication":"https://pith.science/pith/TVHKZUZWSWA23QQ7DQI3LFMXXZ/action/replication_record"}},"created_at":"2026-05-29T00:04:13.744943+00:00","updated_at":"2026-05-29T00:04:13.744943+00:00"}