{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5V2QVIHMHYGIH53RHW2ATBYFUC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbb96b7874512bbc507bb1ca2b226f6ef2eda53d1309fc78ee09d036e5ffac4d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T10:40:55Z","title_canon_sha256":"269407a5692350cd3ce0ac8269731525dbefea9f2423627fbb28a798e68a6a68"},"schema_version":"1.0","source":{"id":"2606.10684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10684","created_at":"2026-06-10T01:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10684v1","created_at":"2026-06-10T01:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10684","created_at":"2026-06-10T01:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"5V2QVIHMHYGI","created_at":"2026-06-10T01:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"5V2QVIHMHYGIH53R","created_at":"2026-06-10T01:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"5V2QVIHM","created_at":"2026-06-10T01:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:faf3387f1a46ceffe08a788d1061041494b5f4bfc875db05121408528e3f260b","target":"graph","created_at":"2026-06-10T01:10:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.10684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language agents which perform multi-step reasoning have shown strong performance in knowledge-intensive question answering. However, existing approaches typically couple evidence acquisition and answer generation within a single policy. This forces a single model to play multiple potentially conflicting roles, inducing a combinatorial explosion in the policy space and hindering efficient exploration. It also introduces a credit assignment problem during training: a search action that retrieves sufficient evidence may still be penalized when generation fails, and vice versa. We propose D","authors_text":"Jaewan Park, Jay-Yoon Lee, Solbee Cho","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T10:40:55Z","title":"Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10684","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8029dcf143d9bcc1002a1724817d301d9d8b0f32f0d8a86e4e612da26a4aa172","target":"record","created_at":"2026-06-10T01:10:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbb96b7874512bbc507bb1ca2b226f6ef2eda53d1309fc78ee09d036e5ffac4d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T10:40:55Z","title_canon_sha256":"269407a5692350cd3ce0ac8269731525dbefea9f2423627fbb28a798e68a6a68"},"schema_version":"1.0","source":{"id":"2606.10684","kind":"arxiv","version":1}},"canonical_sha256":"ed750aa0ec3e0c83f7713db4098705a09fe9484471d0769784945365d9ed4d4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed750aa0ec3e0c83f7713db4098705a09fe9484471d0769784945365d9ed4d4b","first_computed_at":"2026-06-10T01:10:34.203450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:34.203450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g6JHXOUcQWOGmsnwg6x/vwKUNDXmVtqw9xHhPMim3mNBdz1jpWJ58Rz1ex6nYPy74cedZtGKZIg9kEFU3GD2Bg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:34.204285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8029dcf143d9bcc1002a1724817d301d9d8b0f32f0d8a86e4e612da26a4aa172","sha256:faf3387f1a46ceffe08a788d1061041494b5f4bfc875db05121408528e3f260b"],"state_sha256":"c8725c7814ec0ac13b5101962ce549cfff5a725a0986283461042d58b9f3580f"}