{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTO3HXVSFPEZNM4FDYFFWWVMCP","short_pith_number":"pith:NTO3HXVS","schema_version":"1.0","canonical_sha256":"6cddb3deb22bc996b3851e0a5b5aac13d96a23a989bda7af26051296268dd65d","source":{"kind":"arxiv","id":"2410.17195","version":3},"attestation_state":"computed","paper":{"title":"Non-myopic Generation of Language Models for Reasoning and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chang Ma, Haiteng Zhao, Junlei Zhang, Junxian He, Lingpeng Kong","submitted_at":"2024-10-22T17:13:38Z","abstract_excerpt":"Large Language Models have demonstrated remarkable abilities in reasoning and planning by breaking down complex problems into sequential steps. Despite their success in various domains like mathematical problem-solving and coding, LLMs face challenges in ensuring reliable and optimal planning due to their inherent myopic nature of autoregressive decoding. This paper revisits LLM reasoning from an optimal-control perspective, proposing a novel method, Predictive-Decoding, that leverages Model Predictive Control to enhance planning accuracy. By re-weighting LLM distributions based on foresight t"},"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":"2410.17195","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T17:13:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7e47431fb3bd408a8596a78a323a90aeff4854993b69f5179e5f5db36fd410f5","abstract_canon_sha256":"99b2ced776c9a867f74e026627400918b6128cae74aafa101ebdc3c9ec38080c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:06.589740Z","signature_b64":"56FeT9T9qHmH0Rd2BetTP+YjRH8pL8rwLY2p0HDffY+Az6BxvujcGOOzhN5vJ/2hya13eZXxVyqesil/yruxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cddb3deb22bc996b3851e0a5b5aac13d96a23a989bda7af26051296268dd65d","last_reissued_at":"2026-07-05T09:27:06.589231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:06.589231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-myopic Generation of Language Models for Reasoning and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chang Ma, Haiteng Zhao, Junlei Zhang, Junxian He, Lingpeng Kong","submitted_at":"2024-10-22T17:13:38Z","abstract_excerpt":"Large Language Models have demonstrated remarkable abilities in reasoning and planning by breaking down complex problems into sequential steps. Despite their success in various domains like mathematical problem-solving and coding, LLMs face challenges in ensuring reliable and optimal planning due to their inherent myopic nature of autoregressive decoding. This paper revisits LLM reasoning from an optimal-control perspective, proposing a novel method, Predictive-Decoding, that leverages Model Predictive Control to enhance planning accuracy. By re-weighting LLM distributions based on foresight t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17195","kind":"arxiv","version":3},"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/2410.17195/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":"2410.17195","created_at":"2026-07-05T09:27:06.589292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17195v3","created_at":"2026-07-05T09:27:06.589292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17195","created_at":"2026-07-05T09:27:06.589292+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTO3HXVSFPEZ","created_at":"2026-07-05T09:27:06.589292+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTO3HXVSFPEZNM4F","created_at":"2026-07-05T09:27:06.589292+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTO3HXVS","created_at":"2026-07-05T09:27:06.589292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP","json":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP.json","graph_json":"https://pith.science/api/pith-number/NTO3HXVSFPEZNM4FDYFFWWVMCP/graph.json","events_json":"https://pith.science/api/pith-number/NTO3HXVSFPEZNM4FDYFFWWVMCP/events.json","paper":"https://pith.science/paper/NTO3HXVS"},"agent_actions":{"view_html":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP","download_json":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP.json","view_paper":"https://pith.science/paper/NTO3HXVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17195&json=true","fetch_graph":"https://pith.science/api/pith-number/NTO3HXVSFPEZNM4FDYFFWWVMCP/graph.json","fetch_events":"https://pith.science/api/pith-number/NTO3HXVSFPEZNM4FDYFFWWVMCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP/action/storage_attestation","attest_author":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP/action/author_attestation","sign_citation":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP/action/citation_signature","submit_replication":"https://pith.science/pith/NTO3HXVSFPEZNM4FDYFFWWVMCP/action/replication_record"}},"created_at":"2026-07-05T09:27:06.589292+00:00","updated_at":"2026-07-05T09:27:06.589292+00:00"}