{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWD5XKUG3EUVTFDFFWN4H66XMM","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":"e80aa4e39889b9786cc310ff84fb7cdbc9ead11396f9dd7522b41fa5b056b463","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T18:33:48Z","title_canon_sha256":"34a0365d303a652a7236a17d9152295560b03c249906a134bcc6d3ca812a2ec5"},"schema_version":"1.0","source":{"id":"2502.18439","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18439","created_at":"2026-07-05T11:35:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18439v2","created_at":"2026-07-05T11:35:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18439","created_at":"2026-07-05T11:35:53Z"},{"alias_kind":"pith_short_12","alias_value":"XWD5XKUG3EUV","created_at":"2026-07-05T11:35:53Z"},{"alias_kind":"pith_short_16","alias_value":"XWD5XKUG3EUVTFDF","created_at":"2026-07-05T11:35:53Z"},{"alias_kind":"pith_short_8","alias_value":"XWD5XKUG","created_at":"2026-07-05T11:35:53Z"}],"graph_snapshots":[{"event_id":"sha256:23fd590676bb825a50adb6c2614e80b407d1bca6f0f444877c61e9e16e7597ef","target":"graph","created_at":"2026-07-05T11:35:53Z","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/2502.18439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging multiple large language models (LLMs) to build collaborative multi-agentic workflows has demonstrated significant potential. However, most previous studies focus on prompting the out-of-the-box LLMs, relying on their innate capability for collaboration, which may not improve LLMs' performance as shown recently. In this paper, we introduce a new post-training paradigm MAPoRL (Multi-Agent Post-co-training for collaborative LLMs with Reinforcement Learning), to explicitly elicit the collaborative behaviors and further unleash the power of multi-agentic LLM frameworks. In MAPoRL, multip","authors_text":"Asuman Ozdaglar, Chanwoo Park, Joo-Kyung Kim, Kaiqing Zhang, Seungju Han, Xingzhi Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T18:33:48Z","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18439","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:e10c03e8f32d15078718f9f6d727d8eb124fac51997abcd3ad101c1c693a9a0b","target":"record","created_at":"2026-07-05T11:35:53Z","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":"e80aa4e39889b9786cc310ff84fb7cdbc9ead11396f9dd7522b41fa5b056b463","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T18:33:48Z","title_canon_sha256":"34a0365d303a652a7236a17d9152295560b03c249906a134bcc6d3ca812a2ec5"},"schema_version":"1.0","source":{"id":"2502.18439","kind":"arxiv","version":2}},"canonical_sha256":"bd87dbaa86d9295994652d9bc3fbd76320cd9a7787bb9f63f806b718ee9e732c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd87dbaa86d9295994652d9bc3fbd76320cd9a7787bb9f63f806b718ee9e732c","first_computed_at":"2026-07-05T11:35:53.726627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:53.726627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6c40q7HK2zj6ZpGNpKAsQu8MbnrSiImV54b6+sJ8yGXxHT6ZMzcJmIlDGHft+fAxquMDe7WbnxHvHyXdLcf2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:53.727106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18439","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e10c03e8f32d15078718f9f6d727d8eb124fac51997abcd3ad101c1c693a9a0b","sha256:23fd590676bb825a50adb6c2614e80b407d1bca6f0f444877c61e9e16e7597ef"],"state_sha256":"ed5baf6546fe1e07ea7d6d47c14b1af05786600435b2016e6e1e4d158b403055"}