{"id":"261fdb89b5f865e3f392cc4b3e3088da3d087bc34326c81a77485716d0295338","title":"Google DeepMind reports stronger board-game play through search","argument":"Google DeepMind’s page is dated December 4, 2024. It argues that search-based planning improves large language models’ play across chess, Fischer Random Chess, Connect Four and Hex. The authors compare external search, where a model guides Monte Carlo Tree Search rollouts and evaluations, with internal search, where it generates a linearized tree of possible futures and chooses a move. Both approaches build on a model pre-trained with domain knowledge of the games, which the authors say helps it predict game states and legal moves accurately and minimizes hallucinations. The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level performance in chess with a move-count search budget per decision similar to human Grandmasters. Their broader argument is that combining search with domain knowledge could extend beyond board games to language-model inference and training. The abstract does not give the underlying win-rate figures or describe the evaluations in enough detail to assess how broadly the results apply. The suggested extensions beyond games remain a possibility, not a reported demonstration.","topicIds":["artificial-general-intelligence"],"domain":"other","claimType":"attributed reading","limits":"The abstract does not give underlying win-rate figures or enough evaluation detail to assess how broadly the reported results apply. Text as retrieved on November 2, 2026; originally published December 4, 2024.","speaker":{"name":"Google DeepMind","roleAtSource":"Publisher"},"source":{"title":"Mastering Board Games by External and Internal Planning with Language Models","publisher":"Google DeepMind","format":"Article","url":"https://deepmind.google/research/publications/139455/","publishedAt":"2024-12-04T00:00:00+00:00","dateBasis":"Date stated on the publisher’s page."},"evidence":[{"text":"Google DeepMind’s page is dated December 4, 2024.","excerpt":"December 4, 2024\nMastering Board Games by External and Internal Planning with Language Models","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors say search-based planning improves large language models’ playing strength across four board games.","excerpt":"search-based planning can significantly improve LLMs’ playing strength across several board games (Chess, Fischer Random Chess, Connect Four, and Hex).","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors compare external search, which guides Monte Carlo Tree Search rollouts and evaluations, with internal search, which generates a linearized tree of possible futures and a final choice.","excerpt":"In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search,the model directly generates in-context a linearized tree of potential futures and a resulting final choice.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level chess performance with a move-count search budget per decision similar to human Grandmasters.","excerpt":"both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors suggest the approach could extend beyond board games to language-model inference and training.","excerpt":"The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://deepmind.google/research/publications/139455/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well would these search approaches work on language-model tasks beyond board games?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Google DeepMind reports stronger board-game play through search","summary":"Google DeepMind’s page is dated December 4, 2024. It argues that search-based planning improves large language models’ play across chess, Fischer Random Chess, Connect Four and Hex. The authors compare external search, where a model guides Monte Carlo Tree Search rollouts and evaluations, with internal search, where it generates a linearized tree of possible futures and chooses a move. Both approaches build on a model pre-trained with domain knowledge of the games, which the authors say helps it predict game states and legal moves accurately and minimizes hallucinations. The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level performance in chess with a move-count search budget per decision similar to human Grandmasters. Their broader argument is that combining search with domain knowledge could extend beyond board games to language-model inference and training. The abstract does not give the underlying win-rate figures or describe the evaluations in enough detail to assess how broadly the results apply. The suggested extensions beyond games remain a possibility, not a reported demonstration.","question":"How well would these search approaches work on language-model tasks beyond board games?","claims":[{"text":"Google DeepMind’s page is dated December 4, 2024.","excerpt":"December 4, 2024\nMastering Board Games by External and Internal Planning with Language Models","support":"source-stated"},{"text":"The authors say search-based planning improves large language models’ playing strength across four board games.","excerpt":"search-based planning can significantly improve LLMs’ playing strength across several board games (Chess, Fischer Random Chess, Connect Four, and Hex).","support":"source-stated"},{"text":"The authors compare external search, which guides Monte Carlo Tree Search rollouts and evaluations, with internal search, which generates a linearized tree of possible futures and a final choice.","excerpt":"In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search,the model directly generates in-context a linearized tree of potential futures and a resulting final choice.","support":"source-stated"},{"text":"The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level chess performance with a move-count search budget per decision similar to human Grandmasters.","excerpt":"both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters.","support":"source-stated"},{"text":"The authors suggest the approach could extend beyond board games to language-model inference and training.","excerpt":"The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.","support":"source-stated"}],"limitations":["The abstract does not give underlying win-rate figures or enough evaluation detail to assess how broadly the reported results apply.","Text as retrieved on November 2, 2026; originally published December 4, 2024."],"mediaId":null,"correctionReason":null,"id":"261fdb89b5f865e3f392cc4b3e3088da3d087bc34326c81a77485716d0295338","publicationId":"973975e3-b1bf-f62e-de13-5d803bca7a67","version":1,"sourceUrl":"https://deepmind.google/research/publications/139455/","sourceTitle":"Mastering Board Games by External and Internal Planning with Language Models","publisher":"Google DeepMind","publishedAt":"2024-12-04T00:00:00+00:00","originalPublished":{"value":"2024-12-04T00:00:00+00:00","precision":"instant","basis":"backfill:article_published"},"firstObservedAt":"2026-11-02T17:16:14.380Z","createdAt":"2026-11-16T07:03:30.123Z","historical":true,"entityIds":["google-deepmind"],"topicIds":["artificial-general-intelligence"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://deepmind.google/research/publications/139455/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"b0af47b75a1d33ba7657ed8a9f48fb18de61d442936f7e7c2cbaba905dfd1e1e","rubricVersion":"unrecorded","provider":"anthropic","model":"claude-opus-5-5","reasonCodes":["bridge_admitted_by_model","second_opinion_categorical"],"confidence":1,"decidedAt":"2026-11-02T17:16:11.728Z"},"provenance":{"textHash":"9ea4b9c9bd9deefa6dc4f1c7a9f4dbb9c047abc5cb184bce0722544f51424b04","observationId":"247cae61f76a42907cb8fceefc97b9ff5191506f681ed253a78606bb21aba7c8","retrievedAt":"2026-11-02T17:17:24.836Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"a8d49451-8856-1f76-4480-4e58a155cd3d"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"61dbd425-fac7-2e56-210c-842cf9a93b75"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-16T06:59:25.590Z","model":"anthropic/claude-opus-5.5"}},"canonicalUrl":"https://escapemeridian.com/readings/google-deepmind-reports-stronger-board-game-play-through-search-261fdb89","formats":{"html":"/readings/google-deepmind-reports-stronger-board-game-play-through-search-261fdb89","markdown":"/readings/google-deepmind-reports-stronger-board-game-play-through-search-261fdb89.md","json":"/readings/google-deepmind-reports-stronger-board-game-play-through-search-261fdb89.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"conditions":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-pre-training","name":"Pre-training","explanation":"A model's initial training on a large dataset, before further adaptation for particular uses.","referenceUrl":"https://developers.google.com/machine-learning/glossary#pre-training"},{"id":"term-hallucination","name":"Hallucination","explanation":"When an AI system states something false or made up as if it were true.","referenceUrl":"https://developers.google.com/machine-learning/glossary#hallucination"},{"id":"term-inference","name":"Model inference","explanation":"Using a trained model to produce a prediction or response to new input.","referenceUrl":"https://developers.google.com/machine-learning/glossary#inference"}],"entities":[{"id":"google-deepmind","name":"Google DeepMind","kind":"organization","context":"Google DeepMind develops AI systems for general tasks and scientific research, including AlphaFold.","referenceUrls":["https://deepmind.google/blog/","https://deepmind.google/science/alphafold/"],"path":"/entities/google-deepmind","json":"/entities/google-deepmind.json","markdown":"/entities/google-deepmind.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"261fdb89b5f865e3f392cc4b3e3088da3d087bc34326c81a77485716d0295338","revision":"973975e3-b1bf-f62e-de13-5d803bca7a67","revisionKind":"publication-id","title":"Google DeepMind reports stronger board-game play through search","url":"https://escapemeridian.com/readings/google-deepmind-reports-stronger-board-game-play-through-search-261fdb89"},"source":{"type":"source","id":"https://deepmind.google/research/publications/139455/","revision":"9ea4b9c9bd9deefa6dc4f1c7a9f4dbb9c047abc5cb184bce0722544f51424b04","revisionKind":"sha256-source-text","title":"Mastering Board Games by External and Internal Planning with Language Models","url":"https://deepmind.google/research/publications/139455/"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."},"revisions":[{"id":"261fdb89b5f865e3f392cc4b3e3088da3d087bc34326c81a77485716d0295338","title":"Google DeepMind reports stronger board-game play through search","argument":"Google DeepMind’s page is dated December 4, 2024. It argues that search-based planning improves large language models’ play across chess, Fischer Random Chess, Connect Four and Hex. The authors compare external search, where a model guides Monte Carlo Tree Search rollouts and evaluations, with internal search, where it generates a linearized tree of possible futures and chooses a move. Both approaches build on a model pre-trained with domain knowledge of the games, which the authors say helps it predict game states and legal moves accurately and minimizes hallucinations. The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level performance in chess with a move-count search budget per decision similar to human Grandmasters. Their broader argument is that combining search with domain knowledge could extend beyond board games to language-model inference and training. The abstract does not give the underlying win-rate figures or describe the evaluations in enough detail to assess how broadly the results apply. The suggested extensions beyond games remain a possibility, not a reported demonstration.","topicIds":["artificial-general-intelligence"],"domain":"other","claimType":"attributed reading","limits":"The abstract does not give underlying win-rate figures or enough evaluation detail to assess how broadly the reported results apply. Text as retrieved on November 2, 2026; originally published December 4, 2024.","speaker":{"name":"Google DeepMind","roleAtSource":"Publisher"},"source":{"title":"Mastering Board Games by External and Internal Planning with Language Models","publisher":"Google DeepMind","format":"Article","url":"https://deepmind.google/research/publications/139455/","publishedAt":"2024-12-04T00:00:00+00:00","dateBasis":"Date stated on the publisher’s page."},"evidence":[{"text":"Google DeepMind’s page is dated December 4, 2024.","excerpt":"December 4, 2024\nMastering Board Games by External and Internal Planning with Language Models","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors say search-based planning improves large language models’ playing strength across four board games.","excerpt":"search-based planning can significantly improve LLMs’ playing strength across several board games (Chess, Fischer Random Chess, Connect Four, and Hex).","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors compare external search, which guides Monte Carlo Tree Search rollouts and evaluations, with internal search, which generates a linearized tree of possible futures and a final choice.","excerpt":"In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search,the model directly generates in-context a linearized tree of potential futures and a resulting final choice.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level chess performance with a move-count search budget per decision similar to human Grandmasters.","excerpt":"both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"},{"text":"The authors suggest the approach could extend beyond board games to language-model inference and training.","excerpt":"The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.","url":"https://deepmind.google/research/publications/139455/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://deepmind.google/research/publications/139455/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well would these search approaches work on language-model tasks beyond board games?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Google DeepMind reports stronger board-game play through search","summary":"Google DeepMind’s page is dated December 4, 2024. It argues that search-based planning improves large language models’ play across chess, Fischer Random Chess, Connect Four and Hex. The authors compare external search, where a model guides Monte Carlo Tree Search rollouts and evaluations, with internal search, where it generates a linearized tree of possible futures and chooses a move. Both approaches build on a model pre-trained with domain knowledge of the games, which the authors say helps it predict game states and legal moves accurately and minimizes hallucinations. The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level performance in chess with a move-count search budget per decision similar to human Grandmasters. Their broader argument is that combining search with domain knowledge could extend beyond board games to language-model inference and training. The abstract does not give the underlying win-rate figures or describe the evaluations in enough detail to assess how broadly the results apply. The suggested extensions beyond games remain a possibility, not a reported demonstration.","question":"How well would these search approaches work on language-model tasks beyond board games?","claims":[{"text":"Google DeepMind’s page is dated December 4, 2024.","excerpt":"December 4, 2024\nMastering Board Games by External and Internal Planning with Language Models","support":"source-stated"},{"text":"The authors say search-based planning improves large language models’ playing strength across four board games.","excerpt":"search-based planning can significantly improve LLMs’ playing strength across several board games (Chess, Fischer Random Chess, Connect Four, and Hex).","support":"source-stated"},{"text":"The authors compare external search, which guides Monte Carlo Tree Search rollouts and evaluations, with internal search, which generates a linearized tree of possible futures and a final choice.","excerpt":"In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search,the model directly generates in-context a linearized tree of potential futures and a resulting final choice.","support":"source-stated"},{"text":"The authors report improved win-rates against state-of-the-art bots, including Grandmaster-level chess performance with a move-count search budget per decision similar to human Grandmasters.","excerpt":"both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters.","support":"source-stated"},{"text":"The authors suggest the approach could extend beyond board games to language-model inference and training.","excerpt":"The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.","support":"source-stated"}],"limitations":["The abstract does not give underlying win-rate figures or enough evaluation detail to assess how broadly the reported results apply.","Text as retrieved on November 2, 2026; originally published December 4, 2024."],"mediaId":null,"correctionReason":null,"id":"261fdb89b5f865e3f392cc4b3e3088da3d087bc34326c81a77485716d0295338","publicationId":"973975e3-b1bf-f62e-de13-5d803bca7a67","version":1,"sourceUrl":"https://deepmind.google/research/publications/139455/","sourceTitle":"Mastering Board Games by External and Internal Planning with Language Models","publisher":"Google DeepMind","publishedAt":"2024-12-04T00:00:00+00:00","originalPublished":{"value":"2024-12-04T00:00:00+00:00","precision":"instant","basis":"backfill:article_published"},"firstObservedAt":"2026-11-02T17:16:14.380Z","createdAt":"2026-11-16T07:03:30.123Z","historical":true,"entityIds":["google-deepmind"],"topicIds":["artificial-general-intelligence"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://deepmind.google/research/publications/139455/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"b0af47b75a1d33ba7657ed8a9f48fb18de61d442936f7e7c2cbaba905dfd1e1e","rubricVersion":"unrecorded","provider":"anthropic","model":"claude-opus-5-5","reasonCodes":["bridge_admitted_by_model","second_opinion_categorical"],"confidence":1,"decidedAt":"2026-11-02T17:16:11.728Z"},"provenance":{"textHash":"9ea4b9c9bd9deefa6dc4f1c7a9f4dbb9c047abc5cb184bce0722544f51424b04","observationId":"247cae61f76a42907cb8fceefc97b9ff5191506f681ed253a78606bb21aba7c8","retrievedAt":"2026-11-02T17:17:24.836Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"a8d49451-8856-1f76-4480-4e58a155cd3d"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"61dbd425-fac7-2e56-210c-842cf9a93b75"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-16T06:59:25.590Z","model":"anthropic/claude-opus-5.5"}}}],"audits":[{"publicationId":"973975e3-b1bf-f62e-de13-5d803bca7a67","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading attributes the work to Google DeepMind's publication page and its authors, and keeps the findings framed as what the authors argue or report. This matches the page, which presents a single paper abstract with an author list and an arXiv venue.","excerpt":"Mastering Board Games by External and Internal Planning with Language Models"},{"dimension":"summary","status":"uncertain","explanation":"The reading leaves central technical terms unexplained, and the definitions list does not cover them. A non-specialist is not told what Monte Carlo Tree Search, rollouts, a linearized tree of possible futures, or a move-count search budget mean, so the core contrast between external and internal search is hard to follow. Smallest repair: add plain-language tooltips for these terms. Separately, the external-search description drops the source's condition that MCTS runs without calls to an external engine, which is the paper's key distinction. Restore that phrase.","excerpt":"the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine"},{"dimension":"date","status":"pass","explanation":"The reading's December 4, 2024 date matches originalPublished and the page dateline. The page was modified in December 2025, but the cited text is the paper abstract itself, which is plainly the original piece. The reading uses no hindsight framing, presents no forecast as an outcome, and the kind is a publisher page, so no archive disclosure is needed.","excerpt":"December 4, 2024"},{"dimension":"support","status":"pass","explanation":"Each claim traces to the abstract. The win-rate and Grandmaster-level statements stay attributed to the authors. The extensions beyond games are labelled a possibility rather than a demonstration. The question follows from the source's own claim of broader applicability without assuming the answer. The edit after publication does not affect these claims, since they rest on the abstract.","excerpt":"The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques."},{"dimension":"media","status":"pass","explanation":"No media is selected and no verified candidates were supplied, so this is appropriate.","excerpt":null}],"createdAt":"2026-11-16T06:59:25.590Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}