{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FUSOGQMXW3IGXCU46IDSOFCK3G","short_pith_number":"pith:FUSOGQMX","schema_version":"1.0","canonical_sha256":"2d24e34197b6d06b8a9cf20727144ad98d45acdf4a25733210ba5105e73a7bab","source":{"kind":"arxiv","id":"2606.08068","version":1},"attestation_state":"computed","paper":{"title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Bo Liu, Chentao Cao, Yi Xie, Zhanke Zhou","submitted_at":"2026-06-06T09:33:32Z","abstract_excerpt":"Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instability is ill-posed equilibrium selection: current systems specify what information agents share, but not which coordination convention should be selected. We formalize a broad class of such systems as discounted incomplete-information Markov games and show that two common pathologies, oscillation between competing conventions and drift across them, can both induce unstable learning and linear Bayesian regret. To obtai"},"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":"2606.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T09:33:32Z","cross_cats_sorted":[],"title_canon_sha256":"80a33da97884068d3ec7ec4da2913c3b68ce1cdc61eaad20124834271fa004f7","abstract_canon_sha256":"a474fe8712d427ece33243965aa3ddcfe643f28db3452d65e0d52c99f4a45d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:25.257570Z","signature_b64":"EZMXNOsXZjX61btdNs4I0EorIb0SGWQjYHGvDNFONdCJBwFZOf0Yjgvo/e/+VwxdpTD9E/PZInbw98BFp/L4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d24e34197b6d06b8a9cf20727144ad98d45acdf4a25733210ba5105e73a7bab","last_reissued_at":"2026-06-09T01:05:25.257020Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:25.257020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Bo Liu, Chentao Cao, Yi Xie, Zhanke Zhou","submitted_at":"2026-06-06T09:33:32Z","abstract_excerpt":"Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instability is ill-posed equilibrium selection: current systems specify what information agents share, but not which coordination convention should be selected. We formalize a broad class of such systems as discounted incomplete-information Markov games and show that two common pathologies, oscillation between competing conventions and drift across them, can both induce unstable learning and linear Bayesian regret. To obtai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08068","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/2606.08068/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":"2606.08068","created_at":"2026-06-09T01:05:25.257111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08068v1","created_at":"2026-06-09T01:05:25.257111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08068","created_at":"2026-06-09T01:05:25.257111+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUSOGQMXW3IG","created_at":"2026-06-09T01:05:25.257111+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUSOGQMXW3IGXCU4","created_at":"2026-06-09T01:05:25.257111+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUSOGQMX","created_at":"2026-06-09T01:05:25.257111+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/FUSOGQMXW3IGXCU46IDSOFCK3G","json":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G.json","graph_json":"https://pith.science/api/pith-number/FUSOGQMXW3IGXCU46IDSOFCK3G/graph.json","events_json":"https://pith.science/api/pith-number/FUSOGQMXW3IGXCU46IDSOFCK3G/events.json","paper":"https://pith.science/paper/FUSOGQMX"},"agent_actions":{"view_html":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G","download_json":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G.json","view_paper":"https://pith.science/paper/FUSOGQMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08068&json=true","fetch_graph":"https://pith.science/api/pith-number/FUSOGQMXW3IGXCU46IDSOFCK3G/graph.json","fetch_events":"https://pith.science/api/pith-number/FUSOGQMXW3IGXCU46IDSOFCK3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G/action/storage_attestation","attest_author":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G/action/author_attestation","sign_citation":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G/action/citation_signature","submit_replication":"https://pith.science/pith/FUSOGQMXW3IGXCU46IDSOFCK3G/action/replication_record"}},"created_at":"2026-06-09T01:05:25.257111+00:00","updated_at":"2026-06-09T01:05:25.257111+00:00"}