{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NKTIXAR6B2BQB4GQDBTW5GEYTK","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":"a1bf8ecd25efb5d85203527769d0cf626dca53e164a7040021653939d594688d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:09:52Z","title_canon_sha256":"862347181b33f992c6feff34389eb58ec19e802a779bb7b182610e56b93a51ff"},"schema_version":"1.0","source":{"id":"2606.07367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07367","created_at":"2026-06-08T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07367v1","created_at":"2026-06-08T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07367","created_at":"2026-06-08T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"NKTIXAR6B2BQ","created_at":"2026-06-08T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"NKTIXAR6B2BQB4GQ","created_at":"2026-06-08T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"NKTIXAR6","created_at":"2026-06-08T01:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:9d6e973d316f1e01d0704ca61406edc4e04d6ac049981779faba62582e19cefc","target":"graph","created_at":"2026-06-08T01:05:22Z","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/2606.07367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge. A key difficulty lies in credit assignment: agents often receive delayed rewards only at the end of episodes. In this paper, we propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning within a principled in-distribution reinforcement learning paradigm. In each evolving iteration, our method learns an in-di","authors_text":"Meng Fang, Mykola Pechenizkiy, Yudi Zhang, Zhenfang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:09:52Z","title":"Self-evolving LLM agents with in-distribution Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07367","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:fef513c068902e7479e997ea172fc2b0b20e98831cce7b8cbe6d4d505f330a88","target":"record","created_at":"2026-06-08T01:05:22Z","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":"a1bf8ecd25efb5d85203527769d0cf626dca53e164a7040021653939d594688d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:09:52Z","title_canon_sha256":"862347181b33f992c6feff34389eb58ec19e802a779bb7b182610e56b93a51ff"},"schema_version":"1.0","source":{"id":"2606.07367","kind":"arxiv","version":1}},"canonical_sha256":"6aa68b823e0e8300f0d018676e98989aaef26b146093bbecdc326c457e956b5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aa68b823e0e8300f0d018676e98989aaef26b146093bbecdc326c457e956b5e","first_computed_at":"2026-06-08T01:05:22.391701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:22.391701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7TWUpY8jzMQZRaX2gyKXrleodZnyNEpUQBdDLZq3CZCH5wF5mlqnCIUx2FvOWuTYOBS58vps2Xx2RgYx6kZ3CA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:22.392501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fef513c068902e7479e997ea172fc2b0b20e98831cce7b8cbe6d4d505f330a88","sha256:9d6e973d316f1e01d0704ca61406edc4e04d6ac049981779faba62582e19cefc"],"state_sha256":"3b0b4cd8a28002e1c664ad88ad45518cc0eb426edd575b90fbcd9e171e6f3b81"}