{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7C2V7W3EHAK5XJTFSLCYYEEWKO","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":"6d8b7b10222b96d79ad83afa710ef4f31338eedc0dea24d1e7feaee6f0a6eb41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T05:09:49Z","title_canon_sha256":"eaa2d94f71b366342f21eebf41d587d80c734685b5367c56083eebc80416ce30"},"schema_version":"1.0","source":{"id":"2603.02604","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.02604","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.02604v2","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02604","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_12","alias_value":"7C2V7W3EHAK5","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_16","alias_value":"7C2V7W3EHAK5XJTF","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_8","alias_value":"7C2V7W3E","created_at":"2026-05-22T01:03:59Z"}],"graph_snapshots":[{"event_id":"sha256:c0c664982955ff8e8c0a6321053e561d8928b8c6e2386007fa07aee7b1d55c80","target":"graph","created_at":"2026-05-22T01:03:59Z","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/2603.02604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies of isolated multi-agent on-policy optimization. HACRL enables collaborative optimization with independent execution: heterogeneous agents share verified rollouts during training to mutually improve, while operating independently at inference time. Unlike LLM-based multi-agent reinforcement learning (MARL), HACRL does not require coordinated deployment, and unlike on-/off-policy distillation, it enables bidirectional ","authors_text":"Chengyi Yuan, Deqing Wang, Fuzhen Zhuang, Gongxun Li, Huaiyang Wang, Jianxin Li, Ning Ding, Shuai Ma, Xin Xia, Yaodong Yang, Yikun Ban, Zhixia Zhang, Zixuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T05:09:49Z","title":"Heterogeneous Agent Collaborative Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.02604","kind":"arxiv","version":2},"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":"sha256:070612fb046a023229d36b951bbd024c5c624d80a81dc23296df736a7c8be5c4","target":"record","created_at":"2026-05-22T01:03:59Z","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":"6d8b7b10222b96d79ad83afa710ef4f31338eedc0dea24d1e7feaee6f0a6eb41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T05:09:49Z","title_canon_sha256":"eaa2d94f71b366342f21eebf41d587d80c734685b5367c56083eebc80416ce30"},"schema_version":"1.0","source":{"id":"2603.02604","kind":"arxiv","version":2}},"canonical_sha256":"f8b55fdb643815dba66592c58c1096538e9bd31d2f46a94e4acfae2d29d337f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8b55fdb643815dba66592c58c1096538e9bd31d2f46a94e4acfae2d29d337f7","first_computed_at":"2026-05-22T01:03:59.292938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:59.292938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOjqQiFoxfuw8hSF5DWiKDoBf59AAZjPreyS/NG5EeCBvAdT6N4moYjIiALi+zHx14zk8LayCLL2QQ9FLMDNBw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:59.294294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.02604","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070612fb046a023229d36b951bbd024c5c624d80a81dc23296df736a7c8be5c4","sha256:c0c664982955ff8e8c0a6321053e561d8928b8c6e2386007fa07aee7b1d55c80"],"state_sha256":"ca4865c9089efc39e25f62170cb4a3c8798109d63abd46d08d724e21410c82f4"}