{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJ4QLU5YY6T2AWPCEHW4WVO6NQ","short_pith_number":"pith:JJ4QLU5Y","schema_version":"1.0","canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","source":{"kind":"arxiv","id":"2606.05002","version":1},"attestation_state":"computed","paper":{"title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyuan Xie, Yiwen Zhang, Yuqin Huang, Yuxiao Ye, Zhiyuan Liu","submitted_at":"2026-06-03T15:19:55Z","abstract_excerpt":"LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: compe"},"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":"2606.05002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"9f0036cfdf56e983787f8c4be278fc888e1381d0a774838dfb039d62039272ac","abstract_canon_sha256":"fe4c0280d5a257450c2e19144519f75a4be9ebb9420fce89bd8d991bc05d7103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:00.995129Z","signature_b64":"wRABr1e2GpvnoWPC0lIgkadseJiGp2wZI5bglhbTK6AbIqIAj5sZZp6i/Fpuwa/ejG7/8aXTTt1+oOGBDDSfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","last_reissued_at":"2026-06-04T01:10:00.994332Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:00.994332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyuan Xie, Yiwen Zhang, Yuqin Huang, Yuxiao Ye, Zhiyuan Liu","submitted_at":"2026-06-03T15:19:55Z","abstract_excerpt":"LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: compe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05002","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/2606.05002/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":"2606.05002","created_at":"2026-06-04T01:10:00.994464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05002v1","created_at":"2026-06-04T01:10:00.994464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05002","created_at":"2026-06-04T01:10:00.994464+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ4QLU5YY6T2","created_at":"2026-06-04T01:10:00.994464+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ4QLU5YY6T2AWPC","created_at":"2026-06-04T01:10:00.994464+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ4QLU5Y","created_at":"2026-06-04T01:10:00.994464+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/JJ4QLU5YY6T2AWPCEHW4WVO6NQ","json":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ.json","graph_json":"https://pith.science/api/pith-number/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/graph.json","events_json":"https://pith.science/api/pith-number/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/events.json","paper":"https://pith.science/paper/JJ4QLU5Y"},"agent_actions":{"view_html":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ","download_json":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ.json","view_paper":"https://pith.science/paper/JJ4QLU5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05002&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/action/storage_attestation","attest_author":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/action/author_attestation","sign_citation":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/action/citation_signature","submit_replication":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/action/replication_record"}},"created_at":"2026-06-04T01:10:00.994464+00:00","updated_at":"2026-06-04T01:10:00.994464+00:00"}