{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DBGXCGQNLGRXIJ3P6UPYBL4GF6","short_pith_number":"pith:DBGXCGQN","schema_version":"1.0","canonical_sha256":"184d711a0d59a374276ff51f80af862fb383573f6751ade4697279e830bcbbb6","source":{"kind":"arxiv","id":"2402.01118","version":3},"attestation_state":"computed","paper":{"title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ling Liu, Sihao Hu, Tiansheng Huang","submitted_at":"2024-02-02T03:22:12Z","abstract_excerpt":"We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pokemon battles. The design of PokeLLMon incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the panic switching phenomenon when the agent faces a p"},"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":"2402.01118","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-02T03:22:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e8a6459455bf5b9662e62db5b99bc7acd7e6bd6822730ca6eb40f580a5b440a7","abstract_canon_sha256":"bb6d55245bd67b7b9491289a08c5fae9d77e25e00d901a6cdcf897d59c4764ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:29.439124Z","signature_b64":"tsXtlD8UjQ2OxJMcLfcL5Y8Sc2EGc2h0atG9iLh2VhOmo3v9JOmOtMvKs/AZ1vIDy15eJtmHo2KtQRYUYNO9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184d711a0d59a374276ff51f80af862fb383573f6751ade4697279e830bcbbb6","last_reissued_at":"2026-07-05T08:03:29.438728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:29.438728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ling Liu, Sihao Hu, Tiansheng Huang","submitted_at":"2024-02-02T03:22:12Z","abstract_excerpt":"We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pokemon battles. The design of PokeLLMon incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the panic switching phenomenon when the agent faces a p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01118","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/2402.01118/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":"2402.01118","created_at":"2026-07-05T08:03:29.438782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01118v3","created_at":"2026-07-05T08:03:29.438782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01118","created_at":"2026-07-05T08:03:29.438782+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBGXCGQNLGRX","created_at":"2026-07-05T08:03:29.438782+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBGXCGQNLGRXIJ3P","created_at":"2026-07-05T08:03:29.438782+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBGXCGQN","created_at":"2026-07-05T08:03:29.438782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18950","citing_title":"RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10812","citing_title":"PokeRL: Reinforcement Learning for Pokemon Red","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6","json":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6.json","graph_json":"https://pith.science/api/pith-number/DBGXCGQNLGRXIJ3P6UPYBL4GF6/graph.json","events_json":"https://pith.science/api/pith-number/DBGXCGQNLGRXIJ3P6UPYBL4GF6/events.json","paper":"https://pith.science/paper/DBGXCGQN"},"agent_actions":{"view_html":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6","download_json":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6.json","view_paper":"https://pith.science/paper/DBGXCGQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01118&json=true","fetch_graph":"https://pith.science/api/pith-number/DBGXCGQNLGRXIJ3P6UPYBL4GF6/graph.json","fetch_events":"https://pith.science/api/pith-number/DBGXCGQNLGRXIJ3P6UPYBL4GF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6/action/storage_attestation","attest_author":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6/action/author_attestation","sign_citation":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6/action/citation_signature","submit_replication":"https://pith.science/pith/DBGXCGQNLGRXIJ3P6UPYBL4GF6/action/replication_record"}},"created_at":"2026-07-05T08:03:29.438782+00:00","updated_at":"2026-07-05T08:03:29.438782+00:00"}