{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:22QSC6KGPZARMMILRB3BTWWDPZ","short_pith_number":"pith:22QSC6KG","schema_version":"1.0","canonical_sha256":"d6a12179467e4116310b887619dac37e6f80411cb0ef1d8c25b3900e3080759e","source":{"kind":"arxiv","id":"2506.07557","version":1},"attestation_state":"computed","paper":{"title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Zhang, Dongzhan Zhou, Mengsong Wu, Wenliang Chen, Yuqiang Li","submitted_at":"2025-06-09T08:52:27Z","abstract_excerpt":"While Large Language Models (LLMs) have achieved remarkable success in a wide range of applications, their performance often degrades in complex reasoning tasks. In this work, we introduce SELT (Self-Evaluation LLM Tree Search), a novel framework that leverages a modified Monte Carlo Tree Search (MCTS) to enhance LLM reasoning without relying on external reward models. By redefining the Upper Confidence Bound scoring to align with intrinsic self-evaluation capabilities of LLMs and decomposing the inference process into atomic subtasks augmented with semantic clustering at each node, SELT effec"},"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":"2506.07557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:52:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4126397d69d49bbf89038193fd9fb8322ca4843d861e9aa88f82bbada75072c","abstract_canon_sha256":"54dac2a843f6eabdc2336cc13de35c690d5523075265ff52d8787d8235a78270"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:29.404236Z","signature_b64":"mTMfSpXBC3ZTWxhEOjGfR82LmTMBKnsDzR/QMllU/cPJc3jvlijOVRg8iHZrveGtIRZqPsM8UDYR7xiwAAIOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a12179467e4116310b887619dac37e6f80411cb0ef1d8c25b3900e3080759e","last_reissued_at":"2026-07-05T11:18:29.403747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:29.403747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Zhang, Dongzhan Zhou, Mengsong Wu, Wenliang Chen, Yuqiang Li","submitted_at":"2025-06-09T08:52:27Z","abstract_excerpt":"While Large Language Models (LLMs) have achieved remarkable success in a wide range of applications, their performance often degrades in complex reasoning tasks. In this work, we introduce SELT (Self-Evaluation LLM Tree Search), a novel framework that leverages a modified Monte Carlo Tree Search (MCTS) to enhance LLM reasoning without relying on external reward models. By redefining the Upper Confidence Bound scoring to align with intrinsic self-evaluation capabilities of LLMs and decomposing the inference process into atomic subtasks augmented with semantic clustering at each node, SELT effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07557","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/2506.07557/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":"2506.07557","created_at":"2026-07-05T11:18:29.403806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07557v1","created_at":"2026-07-05T11:18:29.403806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07557","created_at":"2026-07-05T11:18:29.403806+00:00"},{"alias_kind":"pith_short_12","alias_value":"22QSC6KGPZAR","created_at":"2026-07-05T11:18:29.403806+00:00"},{"alias_kind":"pith_short_16","alias_value":"22QSC6KGPZARMMIL","created_at":"2026-07-05T11:18:29.403806+00:00"},{"alias_kind":"pith_short_8","alias_value":"22QSC6KG","created_at":"2026-07-05T11:18:29.403806+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/22QSC6KGPZARMMILRB3BTWWDPZ","json":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ.json","graph_json":"https://pith.science/api/pith-number/22QSC6KGPZARMMILRB3BTWWDPZ/graph.json","events_json":"https://pith.science/api/pith-number/22QSC6KGPZARMMILRB3BTWWDPZ/events.json","paper":"https://pith.science/paper/22QSC6KG"},"agent_actions":{"view_html":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ","download_json":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ.json","view_paper":"https://pith.science/paper/22QSC6KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07557&json=true","fetch_graph":"https://pith.science/api/pith-number/22QSC6KGPZARMMILRB3BTWWDPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/22QSC6KGPZARMMILRB3BTWWDPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ/action/storage_attestation","attest_author":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ/action/author_attestation","sign_citation":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ/action/citation_signature","submit_replication":"https://pith.science/pith/22QSC6KGPZARMMILRB3BTWWDPZ/action/replication_record"}},"created_at":"2026-07-05T11:18:29.403806+00:00","updated_at":"2026-07-05T11:18:29.403806+00:00"}