{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NAEZ4V5ZNF6QQLN2ZQRLGMNAMV","short_pith_number":"pith:NAEZ4V5Z","schema_version":"1.0","canonical_sha256":"68099e57b9697d082dbacc22b331a065604c178ca4738be3c0a898f47cf58833","source":{"kind":"arxiv","id":"2309.17179","version":2},"attestation_state":"computed","paper":{"title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jun Wang, Muning Wen, Stephen Marcus McAleer, Weinan Zhang, Xidong Feng, Ying Wen, Ziyu Wan","submitted_at":"2023-09-29T12:20:19Z","abstract_excerpt":"Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a result, these methods will not work in domains where the pre-trained LLM does not have enough knowledge to serve as an effective value function or in domains that require long-horizon planning. To address these limitations, we present an AlphaZero-like tree-search learning framework"},"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":"2309.17179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T12:20:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"387e4fac4b4828b306deb6eea404de80f8626a64abf0732a87f8ee4989751559","abstract_canon_sha256":"ad091de2f8419576136160dfe903f5ff87608392c657c4e167ec5e423f6c5dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:12.617205Z","signature_b64":"nZzPd6H1Nl1c/yMnbBirfqdvq1S9OhAGhhShjMftqXzHJI7oNQd7bMmYQEanZ+tuoNtdKuj7eZvsZJw++ZYpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68099e57b9697d082dbacc22b331a065604c178ca4738be3c0a898f47cf58833","last_reissued_at":"2026-07-05T07:43:12.616688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:12.616688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jun Wang, Muning Wen, Stephen Marcus McAleer, Weinan Zhang, Xidong Feng, Ying Wen, Ziyu Wan","submitted_at":"2023-09-29T12:20:19Z","abstract_excerpt":"Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a result, these methods will not work in domains where the pre-trained LLM does not have enough knowledge to serve as an effective value function or in domains that require long-horizon planning. To address these limitations, we present an AlphaZero-like tree-search learning framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17179","kind":"arxiv","version":2},"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/2309.17179/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":"2309.17179","created_at":"2026-07-05T07:43:12.616755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17179v2","created_at":"2026-07-05T07:43:12.616755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17179","created_at":"2026-07-05T07:43:12.616755+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAEZ4V5ZNF6Q","created_at":"2026-07-05T07:43:12.616755+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAEZ4V5ZNF6QQLN2","created_at":"2026-07-05T07:43:12.616755+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAEZ4V5Z","created_at":"2026-07-05T07:43:12.616755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02390","citing_title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12384","citing_title":"APPO: Agentic Procedural Policy Optimization","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11119","citing_title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08068","citing_title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05464","citing_title":"Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03102","citing_title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20599","citing_title":"Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2504.12334","citing_title":"QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19807","citing_title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03559","citing_title":"DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11340","citing_title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06520","citing_title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2312.08935","citing_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06592","citing_title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10172","citing_title":"V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05262","citing_title":"Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02290","citing_title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19341","citing_title":"Evaluation-driven Scaling for Scientific Discovery","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05868","citing_title":"Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04379","citing_title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05216","citing_title":"SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV","json":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV.json","graph_json":"https://pith.science/api/pith-number/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/graph.json","events_json":"https://pith.science/api/pith-number/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/events.json","paper":"https://pith.science/paper/NAEZ4V5Z"},"agent_actions":{"view_html":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV","download_json":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV.json","view_paper":"https://pith.science/paper/NAEZ4V5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17179&json=true","fetch_graph":"https://pith.science/api/pith-number/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/graph.json","fetch_events":"https://pith.science/api/pith-number/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/action/storage_attestation","attest_author":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/action/author_attestation","sign_citation":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/action/citation_signature","submit_replication":"https://pith.science/pith/NAEZ4V5ZNF6QQLN2ZQRLGMNAMV/action/replication_record"}},"created_at":"2026-07-05T07:43:12.616755+00:00","updated_at":"2026-07-05T07:43:12.616755+00:00"}