{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A647E6PNAFPSHBVIBUFW73LKEW","short_pith_number":"pith:A647E6PN","schema_version":"1.0","canonical_sha256":"07b9f279ed015f2386a80d0b6fed6a25bf20bb613c7617d3bd792d864ccdc8c5","source":{"kind":"arxiv","id":"2502.02508","version":3},"attestation_state":"computed","paper":{"title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuang Gan, David Cox, Gregory Wornell, Guangtao Zeng, Maohao Shen, Subhro Das, Wei Lu, Zhang-Wei Hong, Zhenfang Chen, Zhenting Qi","submitted_at":"2025-02-04T17:26:58Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. This typically involves extensive sampling at inference time guided by an external LLM verifier, resulting in a two-player system. Despite external guidance, the effectiveness of this system demonstrates the potential of a single LLM to tackle complex tasks. Thus, we pose a new research problem: Can we internalize the searching capabilities to fundamentally enhance the reasoning abilities "},"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":"2502.02508","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T17:26:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2cd150fe1bb5ede7ce3d51d396ec686ca4c2ffa725653522d881c14014e0c587","abstract_canon_sha256":"d901509f11a0d03c895e3fd45331cbe0a6f3aa995f69e1e5fdbba9ea223fb034"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:41.634907Z","signature_b64":"KKuK8SjakU+WB+p2dY0L3lVUsYHOhM8oyCp3uUwz1vl+43VAZpsbLxPIQPAa8sh7j7J56c6+Da+gQMjKPQz/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b9f279ed015f2386a80d0b6fed6a25bf20bb613c7617d3bd792d864ccdc8c5","last_reissued_at":"2026-07-05T11:21:41.634351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:41.634351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuang Gan, David Cox, Gregory Wornell, Guangtao Zeng, Maohao Shen, Subhro Das, Wei Lu, Zhang-Wei Hong, Zhenfang Chen, Zhenting Qi","submitted_at":"2025-02-04T17:26:58Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. This typically involves extensive sampling at inference time guided by an external LLM verifier, resulting in a two-player system. Despite external guidance, the effectiveness of this system demonstrates the potential of a single LLM to tackle complex tasks. Thus, we pose a new research problem: Can we internalize the searching capabilities to fundamentally enhance the reasoning abilities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02508","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/2502.02508/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":"2502.02508","created_at":"2026-07-05T11:21:41.634413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02508v3","created_at":"2026-07-05T11:21:41.634413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02508","created_at":"2026-07-05T11:21:41.634413+00:00"},{"alias_kind":"pith_short_12","alias_value":"A647E6PNAFPS","created_at":"2026-07-05T11:21:41.634413+00:00"},{"alias_kind":"pith_short_16","alias_value":"A647E6PNAFPSHBVI","created_at":"2026-07-05T11:21:41.634413+00:00"},{"alias_kind":"pith_short_8","alias_value":"A647E6PN","created_at":"2026-07-05T11:21:41.634413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"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":208,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01075","citing_title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22138","citing_title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20654","citing_title":"REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18851","citing_title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07353","citing_title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW","json":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW.json","graph_json":"https://pith.science/api/pith-number/A647E6PNAFPSHBVIBUFW73LKEW/graph.json","events_json":"https://pith.science/api/pith-number/A647E6PNAFPSHBVIBUFW73LKEW/events.json","paper":"https://pith.science/paper/A647E6PN"},"agent_actions":{"view_html":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW","download_json":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW.json","view_paper":"https://pith.science/paper/A647E6PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02508&json=true","fetch_graph":"https://pith.science/api/pith-number/A647E6PNAFPSHBVIBUFW73LKEW/graph.json","fetch_events":"https://pith.science/api/pith-number/A647E6PNAFPSHBVIBUFW73LKEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW/action/storage_attestation","attest_author":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW/action/author_attestation","sign_citation":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW/action/citation_signature","submit_replication":"https://pith.science/pith/A647E6PNAFPSHBVIBUFW73LKEW/action/replication_record"}},"created_at":"2026-07-05T11:21:41.634413+00:00","updated_at":"2026-07-05T11:21:41.634413+00:00"}