{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LCUU7O5ALQ563DCZA5WAUANSDX","short_pith_number":"pith:LCUU7O5A","schema_version":"1.0","canonical_sha256":"58a94fbba05c3bed8c59076c0a01b21dc69d86607109339740074a541adad37a","source":{"kind":"arxiv","id":"2305.17144","version":2},"attestation_state":"computed","paper":{"title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large language models with text memory and knowledge let agents complete Minecraft's full Overworld item tree for the first time.","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bin Li, Chenxin Tao, Chenyu Yang, Gao Huang, Hao Tian, Jifeng Dai, Lewei Lu, Weijie Su, Xiaogang Wang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Zhaoxiang Zhang","submitted_at":"2023-05-25T17:59:49Z","abstract_excerpt":"The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research landscape predominantly focuses on specific objectives, such as the popular \"ObtainDiamond\" task, and has not yet shown effective generalization to a broader spectrum of tasks. Furthermore, the current leading success rate for the \"ObtainDiamond\" task stands at around 20%, highlighting the limitations of Reinforcement Learning (RL) based controllers used in ex"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2305.17144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-25T17:59:49Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"c6a6442993f95f7eff12801cee554418aba6e2e9c6bee3b86e6177fc9e258ac1","abstract_canon_sha256":"ee054fdaaed73557e9b02b1a341700096ab61fa51c5b6f8e623a1a75e2e287fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.568681Z","signature_b64":"owB6tc4hxAd2JPSFMGO/QsaLIaIx0gqkPeWcaH2kVRaaIM6YEEU2FzBnyIcbrrJj7cYoBFJCW1/GJ4IeB+9gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a94fbba05c3bed8c59076c0a01b21dc69d86607109339740074a541adad37a","last_reissued_at":"2026-05-17T23:38:50.568128Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.568128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large language models with text memory and knowledge let agents complete Minecraft's full Overworld item tree for the first time.","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bin Li, Chenxin Tao, Chenyu Yang, Gao Huang, Hao Tian, Jifeng Dai, Lewei Lu, Weijie Su, Xiaogang Wang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Zhaoxiang Zhang","submitted_at":"2023-05-25T17:59:49Z","abstract_excerpt":"The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research landscape predominantly focuses on specific objectives, such as the popular \"ObtainDiamond\" task, and has not yet shown effective generalization to a broader spectrum of tasks. Furthermore, the current leading success rate for the \"ObtainDiamond\" task stands at around 20%, highlighting the limitations of Reinforcement Learning (RL) based controllers used in ex"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate on the 'ObtainDiamond' task... Notably, our agent is the first to procure all items in the Minecraft Overworld technology tree.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That large language models already contain sufficient logic and common sense to generate reliable long-horizon action plans for sparse-reward open-world tasks when given only text-based state and memory.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GITM uses LLMs to generate action plans from text knowledge and memory, enabling agents to complete long-horizon Minecraft tasks at much higher success rates than prior RL methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large language models with text memory and knowledge let agents complete Minecraft's full Overworld item tree for the first time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"49a8c854c3822a50e5a9b48045d7012b4bf1d57af374abb8d23fbb5a96ed10a1"},"source":{"id":"2305.17144","kind":"arxiv","version":2},"verdict":{"id":"70236ee0-85e4-4b3d-9b37-38c40548c3dc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T18:32:52.638408Z","strongest_claim":"The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate on the 'ObtainDiamond' task... Notably, our agent is the first to procure all items in the Minecraft Overworld technology tree.","one_line_summary":"GITM uses LLMs to generate action plans from text knowledge and memory, enabling agents to complete long-horizon Minecraft tasks at much higher success rates than prior RL methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That large language models already contain sufficient logic and common sense to generate reliable long-horizon action plans for sparse-reward open-world tasks when given only text-based state and memory.","pith_extraction_headline":"Large language models with text memory and knowledge let agents complete Minecraft's full Overworld item tree for the first time."},"references":{"count":45,"sample":[{"doi":"","year":2007,"title":"A. Amiranashvili, N. Dorka, W. Burgard, V . Koltun, and T. Brox. Scaling imitation learning in minecraft. arXiv preprint arXiv:2007.02701, 2020","work_id":"e7b16df6-9e5c-4fac-8a21-737b11f1e8b0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"B. Baker, I. Akkaya, P. Zhokov, J. Huizinga, J. Tang, A. Ecoffet, B. Houghton, R. Sampedro, and J. Clune. Video pretraining (vpt): Learning to act by watching unlabeled online videos. Advances in Neur","work_id":"75b9b01d-e05c-4cc5-aa7d-f927f9399a9e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Open-world multi-task control through goal-aware representation learning and adaptive horizon prediction","work_id":"af3d3319-28aa-4659-b04a-04dd057709b2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"PaLM-E: An Embodied Multimodal Language Model","work_id":"5b99811a-1d93-47e2-9d59-f4045a0b74a2","ref_index":4,"cited_arxiv_id":"2303.03378","is_internal_anchor":true},{"doi":"","year":2022,"title":"doi:10.48550/arXiv.2206.08853 , author =","work_id":"ded038df-ed98-4558-8bab-af5a5338aad5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"1057049b21a3a2b89d97c09f654924fa318a81f36fcdd8ad013c4404d244ab20","internal_anchors":10},"formal_canon":{"evidence_count":3,"snapshot_sha256":"c8edf64d1837e8b0cd2d509dfdec619ef87a05a68e713467314e60c349ee11e3"},"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":"2305.17144","created_at":"2026-05-17T23:38:50.568236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17144v2","created_at":"2026-05-17T23:38:50.568236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17144","created_at":"2026-05-17T23:38:50.568236+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCUU7O5ALQ56","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCUU7O5ALQ563DCZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCUU7O5A","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":193,"is_internal_anchor":true},{"citing_arxiv_id":"2502.08691","citing_title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22566","citing_title":"GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2310.02170","citing_title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07066","citing_title":"2.5-D Decomposition for LLM-Based Spatial Construction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":209,"is_internal_anchor":true},{"citing_arxiv_id":"2511.02805","citing_title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2504.15965","citing_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2603.00977","citing_title":"HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2305.19118","citing_title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26622","citing_title":"OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07202","citing_title":"Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18975","citing_title":"Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11655","citing_title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08340","citing_title":"PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07202","citing_title":"Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07066","citing_title":"2.5-D Decomposition for LLM-Based Spatial Construction","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX","json":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX.json","graph_json":"https://pith.science/api/pith-number/LCUU7O5ALQ563DCZA5WAUANSDX/graph.json","events_json":"https://pith.science/api/pith-number/LCUU7O5ALQ563DCZA5WAUANSDX/events.json","paper":"https://pith.science/paper/LCUU7O5A"},"agent_actions":{"view_html":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX","download_json":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX.json","view_paper":"https://pith.science/paper/LCUU7O5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17144&json=true","fetch_graph":"https://pith.science/api/pith-number/LCUU7O5ALQ563DCZA5WAUANSDX/graph.json","fetch_events":"https://pith.science/api/pith-number/LCUU7O5ALQ563DCZA5WAUANSDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX/action/storage_attestation","attest_author":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX/action/author_attestation","sign_citation":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX/action/citation_signature","submit_replication":"https://pith.science/pith/LCUU7O5ALQ563DCZA5WAUANSDX/action/replication_record"}},"created_at":"2026-05-17T23:38:50.568236+00:00","updated_at":"2026-05-17T23:38:50.568236+00:00"}