{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXZZ2N4MSOI747P3PWUACNF4MD","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":"e1d873611dd02e965635563f3bd73470f1771bdb475bf598494de344a5a67812","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T14:01:44Z","title_canon_sha256":"7b376f3723d35b0d21e9860057e0c388bb4a24a75a34f736b9e22f34e4ab6ea3"},"schema_version":"1.0","source":{"id":"2405.15821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15821","created_at":"2026-07-05T08:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15821v1","created_at":"2026-07-05T08:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15821","created_at":"2026-07-05T08:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"LXZZ2N4MSOI7","created_at":"2026-07-05T08:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"LXZZ2N4MSOI747P3","created_at":"2026-07-05T08:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"LXZZ2N4M","created_at":"2026-07-05T08:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:63d7b0efae3c0011df80fd19d7870d604155269fef70b3d4e3f2af742272e10e","target":"graph","created_at":"2026-07-05T08:22:57Z","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/2405.15821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models as intelligent agents push the boundaries of sequential decision-making agents but struggle with limited knowledge of environmental dynamics and exponentially huge action space. Recent efforts like GLAM and TWOSOME manually constrain the action space to a restricted subset and employ reinforcement learning to align agents' knowledge with specific environments. However, they overlook fine-grained credit assignments for intra-action tokens, which is essential for efficient language agent optimization, and rely on human's prior knowledge to restrict action space. This paper propos","authors_text":"Jun Wang, Muning Wen, Weinan Zhang, Ying Wen, Ziyu Wan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15821","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:e49409fd4f7afa827a5a00aadbbfad34c0107cb4d0acbe03676179b4ad3a2750","target":"record","created_at":"2026-07-05T08:22:57Z","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":"e1d873611dd02e965635563f3bd73470f1771bdb475bf598494de344a5a67812","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T14:01:44Z","title_canon_sha256":"7b376f3723d35b0d21e9860057e0c388bb4a24a75a34f736b9e22f34e4ab6ea3"},"schema_version":"1.0","source":{"id":"2405.15821","kind":"arxiv","version":1}},"canonical_sha256":"5df39d378c9391fe7dfb7da80134bc60f787b5e5adbefbfdf6d2c849cca864e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5df39d378c9391fe7dfb7da80134bc60f787b5e5adbefbfdf6d2c849cca864e2","first_computed_at":"2026-07-05T08:22:57.274085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:57.274085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J/21gIwcwPJz22T4xqZYyDbL2l4TBdC4mzCeCHopBZJArezlhMld98xP/rUeeUGs0y3h5rDHQPQtcx8osISoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:57.274678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e49409fd4f7afa827a5a00aadbbfad34c0107cb4d0acbe03676179b4ad3a2750","sha256:63d7b0efae3c0011df80fd19d7870d604155269fef70b3d4e3f2af742272e10e"],"state_sha256":"09aa1d7824d4a7362c1342f8588432dee2a783dede1d74e5163ecab270fe58f4"}