{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ELG3LBCXP2TT6K2M4BMQYEUKGU","short_pith_number":"pith:ELG3LBCX","schema_version":"1.0","canonical_sha256":"22cdb584577ea73f2b4ce0590c128a3523836f14bad730d876abe143c950612c","source":{"kind":"arxiv","id":"2501.09891","version":1},"attestation_state":"computed","paper":{"title":"Evolving Deeper LLM Thinking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dale Schuurmans, Dave Marwood, Ian Fischer, Kuang-Huei Lee, Shumeet Baluja, Xinyun Chen, Yueh-Hua Wu","submitted_at":"2025-01-17T00:41:44Z","abstract_excerpt":"We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolut"},"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":"2501.09891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T00:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"1ba0695143f2afa1d7af86085621b0caa61eecb53a70502856ac9121f4f9b8cc","abstract_canon_sha256":"1edad2ae69becd8fc808e567d62e1a2f020e6cd5bc9d298c272b9baecf690696"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:13.037964Z","signature_b64":"TONXb3+nu2T5KGviEJivZvcWZ+iSO5T2N2qdROHk1a9Q4hCqRDOoMkg+kmbmSlDzlTJIWXlLqoYtwuBp63OfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22cdb584577ea73f2b4ce0590c128a3523836f14bad730d876abe143c950612c","last_reissued_at":"2026-07-05T10:02:13.037569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:13.037569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolving Deeper LLM Thinking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dale Schuurmans, Dave Marwood, Ian Fischer, Kuang-Huei Lee, Shumeet Baluja, Xinyun Chen, Yueh-Hua Wu","submitted_at":"2025-01-17T00:41:44Z","abstract_excerpt":"We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09891","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/2501.09891/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":"2501.09891","created_at":"2026-07-05T10:02:13.037636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09891v1","created_at":"2026-07-05T10:02:13.037636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09891","created_at":"2026-07-05T10:02:13.037636+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELG3LBCXP2TT","created_at":"2026-07-05T10:02:13.037636+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELG3LBCXP2TT6K2M","created_at":"2026-07-05T10:02:13.037636+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELG3LBCX","created_at":"2026-07-05T10:02:13.037636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18910","citing_title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20625","citing_title":"AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22102","citing_title":"ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18850","citing_title":"Cognitive Alpha Mining via LLM-Driven Code-Based Evolution","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13874","citing_title":"GEAR: Genetic AutoResearch for Agentic Code Evolution","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01348","citing_title":"Procedural Knowledge at Scale Improves Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06219","citing_title":"Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08299","citing_title":"SeLaR: Selective Latent Reasoning in Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17433","citing_title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU","json":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU.json","graph_json":"https://pith.science/api/pith-number/ELG3LBCXP2TT6K2M4BMQYEUKGU/graph.json","events_json":"https://pith.science/api/pith-number/ELG3LBCXP2TT6K2M4BMQYEUKGU/events.json","paper":"https://pith.science/paper/ELG3LBCX"},"agent_actions":{"view_html":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU","download_json":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU.json","view_paper":"https://pith.science/paper/ELG3LBCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09891&json=true","fetch_graph":"https://pith.science/api/pith-number/ELG3LBCXP2TT6K2M4BMQYEUKGU/graph.json","fetch_events":"https://pith.science/api/pith-number/ELG3LBCXP2TT6K2M4BMQYEUKGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU/action/storage_attestation","attest_author":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU/action/author_attestation","sign_citation":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU/action/citation_signature","submit_replication":"https://pith.science/pith/ELG3LBCXP2TT6K2M4BMQYEUKGU/action/replication_record"}},"created_at":"2026-07-05T10:02:13.037636+00:00","updated_at":"2026-07-05T10:02:13.037636+00:00"}