{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AOGCDBIKXFCA63SMPTPHUGWFL6","short_pith_number":"pith:AOGCDBIK","schema_version":"1.0","canonical_sha256":"038c21850ab9440f6e4c7cde7a1ac55f90d49f2d17e085119cd87dc882e77397","source":{"kind":"arxiv","id":"2606.20014","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Amir Baghi, Florian Fuchs, Jannik H\\\"osch, Jean-Philippe Barrette-LaPierre, Joakim Bergdahl, Konrad Tollmar, Linus Gissl\\'en","submitted_at":"2026-06-18T09:47:06Z","abstract_excerpt":"Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment a"},"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":"2606.20014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T09:47:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a7aa8a60b0ff97a3d294984e59425ae3c8469ab65911641aeb41246bc0a9ca2","abstract_canon_sha256":"3e43fe094116fb37ab3fb728f4eb5f92f8ef92dcb87c0703438b06b9f503f95a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:00.720685Z","signature_b64":"6/Dc0t05l/MEiLhPYAOZglWMdOJZbVeYCoJe4r893WxP41Sa++mkiHR2z2C7dmEDdvJe4k9ZXJYnwxaIqXJbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038c21850ab9440f6e4c7cde7a1ac55f90d49f2d17e085119cd87dc882e77397","last_reissued_at":"2026-06-19T16:13:00.720293Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:00.720293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Amir Baghi, Florian Fuchs, Jannik H\\\"osch, Jean-Philippe Barrette-LaPierre, Joakim Bergdahl, Konrad Tollmar, Linus Gissl\\'en","submitted_at":"2026-06-18T09:47:06Z","abstract_excerpt":"Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20014","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/2606.20014/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":"2606.20014","created_at":"2026-06-19T16:13:00.720369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20014v1","created_at":"2026-06-19T16:13:00.720369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20014","created_at":"2026-06-19T16:13:00.720369+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOGCDBIKXFCA","created_at":"2026-06-19T16:13:00.720369+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOGCDBIKXFCA63SM","created_at":"2026-06-19T16:13:00.720369+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOGCDBIK","created_at":"2026-06-19T16:13:00.720369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6","json":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6.json","graph_json":"https://pith.science/api/pith-number/AOGCDBIKXFCA63SMPTPHUGWFL6/graph.json","events_json":"https://pith.science/api/pith-number/AOGCDBIKXFCA63SMPTPHUGWFL6/events.json","paper":"https://pith.science/paper/AOGCDBIK"},"agent_actions":{"view_html":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6","download_json":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6.json","view_paper":"https://pith.science/paper/AOGCDBIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20014&json=true","fetch_graph":"https://pith.science/api/pith-number/AOGCDBIKXFCA63SMPTPHUGWFL6/graph.json","fetch_events":"https://pith.science/api/pith-number/AOGCDBIKXFCA63SMPTPHUGWFL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6/action/storage_attestation","attest_author":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6/action/author_attestation","sign_citation":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6/action/citation_signature","submit_replication":"https://pith.science/pith/AOGCDBIKXFCA63SMPTPHUGWFL6/action/replication_record"}},"created_at":"2026-06-19T16:13:00.720369+00:00","updated_at":"2026-06-19T16:13:00.720369+00:00"}