{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VY7DSE6JJE3OPJCSPMCDDPPS6J","short_pith_number":"pith:VY7DSE6J","schema_version":"1.0","canonical_sha256":"ae3e3913c94936e7a4527b0431bdf2f27f9845508213834d49e4f98fd95c295e","source":{"kind":"arxiv","id":"2606.17591","version":1},"attestation_state":"computed","paper":{"title":"Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanghui Wang, Li Shao, Peiyang He, Xiaofeng Shi, Xing Zhang, Yanwei Cui, Yulong Zhang","submitted_at":"2026-06-16T06:55:55Z","abstract_excerpt":"Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes. However, in non-stationary environments these agents face a retention-forgetting dilemma: retaining stale insights causes negative transfer, while discarding them causes catastrophic forgetting when conditions recur. We identify four requirements for navigating this dilemma -- outcome-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.17591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T06:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d201431b2054cd303df0f811cb598d820aaf4810fb000dbd681455bfbcb5175","abstract_canon_sha256":"e4b11f1d293659f1192e2da780b7c82b7287b975de19faa2871bd42989ba55d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:16.748007Z","signature_b64":"uoHfl8d3hGVKtsQIWSSHrn2SmMvv+n2bQXuUa8PPEnqg2Lgwf99nugSrFu/wh/OkZp7FdsPVizMo5KoIugaHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3e3913c94936e7a4527b0431bdf2f27f9845508213834d49e4f98fd95c295e","last_reissued_at":"2026-06-19T16:10:16.747616Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:16.747616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanghui Wang, Li Shao, Peiyang He, Xiaofeng Shi, Xing Zhang, Yanwei Cui, Yulong Zhang","submitted_at":"2026-06-16T06:55:55Z","abstract_excerpt":"Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes. However, in non-stationary environments these agents face a retention-forgetting dilemma: retaining stale insights causes negative transfer, while discarding them causes catastrophic forgetting when conditions recur. We identify four requirements for navigating this dilemma -- outcome-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17591","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.17591/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.17591","created_at":"2026-06-19T16:10:16.747678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17591v1","created_at":"2026-06-19T16:10:16.747678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17591","created_at":"2026-06-19T16:10:16.747678+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY7DSE6JJE3O","created_at":"2026-06-19T16:10:16.747678+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY7DSE6JJE3OPJCS","created_at":"2026-06-19T16:10:16.747678+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY7DSE6J","created_at":"2026-06-19T16:10:16.747678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J","json":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J.json","graph_json":"https://pith.science/api/pith-number/VY7DSE6JJE3OPJCSPMCDDPPS6J/graph.json","events_json":"https://pith.science/api/pith-number/VY7DSE6JJE3OPJCSPMCDDPPS6J/events.json","paper":"https://pith.science/paper/VY7DSE6J"},"agent_actions":{"view_html":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J","download_json":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J.json","view_paper":"https://pith.science/paper/VY7DSE6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17591&json=true","fetch_graph":"https://pith.science/api/pith-number/VY7DSE6JJE3OPJCSPMCDDPPS6J/graph.json","fetch_events":"https://pith.science/api/pith-number/VY7DSE6JJE3OPJCSPMCDDPPS6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J/action/storage_attestation","attest_author":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J/action/author_attestation","sign_citation":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J/action/citation_signature","submit_replication":"https://pith.science/pith/VY7DSE6JJE3OPJCSPMCDDPPS6J/action/replication_record"}},"created_at":"2026-06-19T16:10:16.747678+00:00","updated_at":"2026-06-19T16:10:16.747678+00:00"}