{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7CMZH6GWCBSKD3YZXWLB5OCQC","short_pith_number":"pith:N7CMZH6G","schema_version":"1.0","canonical_sha256":"6fc4cc9fc6b083250f78cdecb0f5c280a91797ba8af54c1677d8667c227fd9f3","source":{"kind":"arxiv","id":"2508.06042","version":1},"attestation_state":"computed","paper":{"title":"Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daechul Ahn, Jonghyun Choi, San Kim","submitted_at":"2025-08-08T05:57:12Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents need to manage resource constraints and adapt to evolving battlefield situations in a partially observable environment. This often overwhelms exisiting LLM-based approaches. To address these challenges, we propose a hierarchical multi-agent framework that employs specialized imitation learning agents under a meta-controller called Strategic Planner (SP). By 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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.06042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-08T05:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"a5087f5f9139b90fc47666870b947c4da1d82fa628d722f9f02e0b887e8fefd5","abstract_canon_sha256":"65f5b3f06ad43a0f5d58069ee7b1f2c18f50a0c0d1d52eeef0314ba3a75d2ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:48.081045Z","signature_b64":"9cIYt7OVd95zOK45l8RHVTL2sn6vErtxrlUugxSxurqMFgH+Z+ufAr6UZdlp5lH3hPxP+N6X0+RhOogBMKBQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc4cc9fc6b083250f78cdecb0f5c280a91797ba8af54c1677d8667c227fd9f3","last_reissued_at":"2026-07-05T11:50:48.080547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:48.080547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daechul Ahn, Jonghyun Choi, San Kim","submitted_at":"2025-08-08T05:57:12Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents need to manage resource constraints and adapt to evolving battlefield situations in a partially observable environment. This often overwhelms exisiting LLM-based approaches. To address these challenges, we propose a hierarchical multi-agent framework that employs specialized imitation learning agents under a meta-controller called Strategic Planner (SP). By ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06042","kind":"arxiv","version":1},"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/2508.06042/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":"2508.06042","created_at":"2026-07-05T11:50:48.080604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06042v1","created_at":"2026-07-05T11:50:48.080604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06042","created_at":"2026-07-05T11:50:48.080604+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7CMZH6GWCBS","created_at":"2026-07-05T11:50:48.080604+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7CMZH6GWCBSKD3Y","created_at":"2026-07-05T11:50:48.080604+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7CMZH6G","created_at":"2026-07-05T11:50:48.080604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15972","citing_title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC","json":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC.json","graph_json":"https://pith.science/api/pith-number/N7CMZH6GWCBSKD3YZXWLB5OCQC/graph.json","events_json":"https://pith.science/api/pith-number/N7CMZH6GWCBSKD3YZXWLB5OCQC/events.json","paper":"https://pith.science/paper/N7CMZH6G"},"agent_actions":{"view_html":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC","download_json":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC.json","view_paper":"https://pith.science/paper/N7CMZH6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06042&json=true","fetch_graph":"https://pith.science/api/pith-number/N7CMZH6GWCBSKD3YZXWLB5OCQC/graph.json","fetch_events":"https://pith.science/api/pith-number/N7CMZH6GWCBSKD3YZXWLB5OCQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC/action/storage_attestation","attest_author":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC/action/author_attestation","sign_citation":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC/action/citation_signature","submit_replication":"https://pith.science/pith/N7CMZH6GWCBSKD3YZXWLB5OCQC/action/replication_record"}},"created_at":"2026-07-05T11:50:48.080604+00:00","updated_at":"2026-07-05T11:50:48.080604+00:00"}