{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HPWKLIRFEMYOACML5FHLMSASTD","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":"e2f6cb5205d544b284fe428648cb1394f4594a14b12c125721c0cfaeda0c8e61","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:45:56Z","title_canon_sha256":"d1d7f17cab12ea5d98f991ec66f1b6b8e3672a4b30b44d508fec5be83ab7bb31"},"schema_version":"1.0","source":{"id":"2402.19446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19446","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19446v1","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19446","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"HPWKLIRFEMYO","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"HPWKLIRFEMYOACML","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"HPWKLIRF","created_at":"2026-07-05T07:50:45Z"}],"graph_snapshots":[{"event_id":"sha256:1016da5d3208694dd831a790e1539dcfcfb74b395313f0318bab688c6bbbf2e7","target":"graph","created_at":"2026-07-05T07:50:45Z","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/2402.19446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A broad use case of large language models (LLMs) is in goal-directed decision-making tasks (or \"agent\" tasks), where an LLM needs to not just generate completions for a given prompt, but rather make intelligent decisions over a multi-turn interaction to accomplish a task (e.g., when interacting with the web, using tools, or providing customer support). Reinforcement learning (RL) provides a general paradigm to address such agent tasks, but current RL methods for LLMs largely focus on optimizing single-turn rewards. By construction, most single-turn RL methods cannot endow LLMs with the ability","authors_text":"Andrea Zanette, Aviral Kumar, Jiayi Pan, Sergey Levine, Yifei Zhou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:45:56Z","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19446","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:ef0464f7d756c21d6609ff6d4b527b031459472dca3105672d91f085ceede36f","target":"record","created_at":"2026-07-05T07:50:45Z","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":"e2f6cb5205d544b284fe428648cb1394f4594a14b12c125721c0cfaeda0c8e61","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:45:56Z","title_canon_sha256":"d1d7f17cab12ea5d98f991ec66f1b6b8e3672a4b30b44d508fec5be83ab7bb31"},"schema_version":"1.0","source":{"id":"2402.19446","kind":"arxiv","version":1}},"canonical_sha256":"3beca5a2252330e0098be94eb6481298e07caad7945ab7df9824a8fa0ffe699c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3beca5a2252330e0098be94eb6481298e07caad7945ab7df9824a8fa0ffe699c","first_computed_at":"2026-07-05T07:50:45.373181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:45.373181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmMU4T5yUTtQ/1EAIQIhwwhXPN8qMpluiQXSgQS9UL0x6nW6Iooj5EU8PbfX/OKI32IxaH6NbTCrTnql+KxPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:45.373678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef0464f7d756c21d6609ff6d4b527b031459472dca3105672d91f085ceede36f","sha256:1016da5d3208694dd831a790e1539dcfcfb74b395313f0318bab688c6bbbf2e7"],"state_sha256":"bccdc7b38ba482d1b8e82ed6ba79d1cf2d68e3d77093f043a2698d18b3f27adb"}