{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y45YWD6TTG5A5G3TH23BP4TFOB","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":"0ed552d53f383ea11db8448cf90f3882261c4197efa360374118d470835cde52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T17:55:08Z","title_canon_sha256":"6e6d4c0b70697aed83a116067bb9186c310ed5df7164b183c8b9def354f8587c"},"schema_version":"1.0","source":{"id":"2503.15478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15478","created_at":"2026-07-05T10:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15478v1","created_at":"2026-07-05T10:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15478","created_at":"2026-07-05T10:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"Y45YWD6TTG5A","created_at":"2026-07-05T10:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"Y45YWD6TTG5A5G3T","created_at":"2026-07-05T10:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"Y45YWD6T","created_at":"2026-07-05T10:35:27Z"}],"graph_snapshots":[{"event_id":"sha256:857220226cc274bcc4e9ae2169a923cec31fc9935b8cc8eb8fdb6ad969fbc65c","target":"graph","created_at":"2026-07-05T10:35:27Z","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/2503.15478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs and it remains unclear how to develop such algorithms. To study this, we first introduce a new benchmark, ColBench, where an LLM agent interacts with a human collaborator over multiple turns to solve realistic tasks in backend programming and frontend design. Building on this benchmark, we propose a novel RL algor","authors_text":"Jason Weston, Sainbayar Sukhbaatar, Sergey Levine, Song Jiang, Xian Li, Yifei Zhou, Yuandong Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T17:55:08Z","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15478","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":"sha256:2d0517b244e098e77dc7c0d5cfb6df77adae11119952b1b6aeadeee55fa35afc","target":"record","created_at":"2026-07-05T10:35:27Z","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":"0ed552d53f383ea11db8448cf90f3882261c4197efa360374118d470835cde52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T17:55:08Z","title_canon_sha256":"6e6d4c0b70697aed83a116067bb9186c310ed5df7164b183c8b9def354f8587c"},"schema_version":"1.0","source":{"id":"2503.15478","kind":"arxiv","version":1}},"canonical_sha256":"c73b8b0fd399ba0e9b733eb617f265705c2603fa4f084ca2832f6ee72ba6dfba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c73b8b0fd399ba0e9b733eb617f265705c2603fa4f084ca2832f6ee72ba6dfba","first_computed_at":"2026-07-05T10:35:27.158682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:27.158682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rn/kZQba+NP2AgIXOhrq5skANo8dY1mOaUAqyohJLK21inXROGNj6I97f90pOwg0WGuFswggAs1p01rP4cyKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:27.159610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d0517b244e098e77dc7c0d5cfb6df77adae11119952b1b6aeadeee55fa35afc","sha256:857220226cc274bcc4e9ae2169a923cec31fc9935b8cc8eb8fdb6ad969fbc65c"],"state_sha256":"d794e126ed1663de729a8dc7eebac1563c1a7a42d438717c5a77a27dc4b25c7b"}