{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22HF37HRLRA2L2HM2HNB6SY5N6","short_pith_number":"pith:22HF37HR","schema_version":"1.0","canonical_sha256":"d68e5dfcf15c41a5e8ecd1da1f4b1d6fb1a5d2184ffca0f46776f0e2e0c501c0","source":{"kind":"arxiv","id":"2412.12119","version":3},"attestation_state":"computed","paper":{"title":"Mastering Board Games by External and Internal Planning with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Anian Ruoss, Cannada Lewis, Daniel Hennes, Eric Malmi, Jakub Adamek, Jeremy Shar, John Schultz, Laurel Prince, Marc Lanctot, Matej Jusup, Michael Kaisers, Nenad Toma\\v{s}ev, Petar Veli\\v{c}kovi\\'c, Sarah Perrin, Satinder Singh, Tom Zahavy","submitted_at":"2024-12-02T18:56:51Z","abstract_excerpt":"Advancing planning and reasoning capabilities of Large Language Models (LLMs) is one of the key prerequisites towards unlocking their potential for performing reliably in complex and impactful domains. In this paper, we aim to demonstrate this across board games (Chess, Fischer Random / Chess960, Connect Four, and Hex), and we show that search-based planning can yield significant improvements in LLM game-playing strength. We introduce, compare and contrast two major approaches: In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an exte"},"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":"2412.12119","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-02T18:56:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3bf0e93617e6da9837598ed02aea3b78998ad374a844d250ab93abe26d1b2dde","abstract_canon_sha256":"471e0b6951cd42ddc80fde5338839c05b725e2954415a5d8b61cd66b29dce023"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:14.365865Z","signature_b64":"th8lGd4Cx9YdY8AIT7gO7Kz+AGMPxtrAVwDrc63DDJXX1JXR8kqzljUMKJ+uWGRyuN3w8h81zSO3WWdAf9G8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d68e5dfcf15c41a5e8ecd1da1f4b1d6fb1a5d2184ffca0f46776f0e2e0c501c0","last_reissued_at":"2026-07-05T11:08:14.365340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:14.365340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering Board Games by External and Internal Planning with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Anian Ruoss, Cannada Lewis, Daniel Hennes, Eric Malmi, Jakub Adamek, Jeremy Shar, John Schultz, Laurel Prince, Marc Lanctot, Matej Jusup, Michael Kaisers, Nenad Toma\\v{s}ev, Petar Veli\\v{c}kovi\\'c, Sarah Perrin, Satinder Singh, Tom Zahavy","submitted_at":"2024-12-02T18:56:51Z","abstract_excerpt":"Advancing planning and reasoning capabilities of Large Language Models (LLMs) is one of the key prerequisites towards unlocking their potential for performing reliably in complex and impactful domains. In this paper, we aim to demonstrate this across board games (Chess, Fischer Random / Chess960, Connect Four, and Hex), and we show that search-based planning can yield significant improvements in LLM game-playing strength. We introduce, compare and contrast two major approaches: In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an exte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12119","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/2412.12119/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":"2412.12119","created_at":"2026-07-05T11:08:14.365409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12119v3","created_at":"2026-07-05T11:08:14.365409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12119","created_at":"2026-07-05T11:08:14.365409+00:00"},{"alias_kind":"pith_short_12","alias_value":"22HF37HRLRA2","created_at":"2026-07-05T11:08:14.365409+00:00"},{"alias_kind":"pith_short_16","alias_value":"22HF37HRLRA2L2HM","created_at":"2026-07-05T11:08:14.365409+00:00"},{"alias_kind":"pith_short_8","alias_value":"22HF37HR","created_at":"2026-07-05T11:08:14.365409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03685","citing_title":"A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24375","citing_title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06840","citing_title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06840","citing_title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06840","citing_title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06840","citing_title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06840","citing_title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6","json":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6.json","graph_json":"https://pith.science/api/pith-number/22HF37HRLRA2L2HM2HNB6SY5N6/graph.json","events_json":"https://pith.science/api/pith-number/22HF37HRLRA2L2HM2HNB6SY5N6/events.json","paper":"https://pith.science/paper/22HF37HR"},"agent_actions":{"view_html":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6","download_json":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6.json","view_paper":"https://pith.science/paper/22HF37HR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12119&json=true","fetch_graph":"https://pith.science/api/pith-number/22HF37HRLRA2L2HM2HNB6SY5N6/graph.json","fetch_events":"https://pith.science/api/pith-number/22HF37HRLRA2L2HM2HNB6SY5N6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6/action/storage_attestation","attest_author":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6/action/author_attestation","sign_citation":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6/action/citation_signature","submit_replication":"https://pith.science/pith/22HF37HRLRA2L2HM2HNB6SY5N6/action/replication_record"}},"created_at":"2026-07-05T11:08:14.365409+00:00","updated_at":"2026-07-05T11:08:14.365409+00:00"}