{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XGEYBB5IEAFSV5X76B6S6VQLZZ","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":"c3e2cf631c4a86bf072b14490ee085a8e187c252a33a33653acb2f2e6c1a3e1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T08:08:18Z","title_canon_sha256":"137024064bd0682326b7aa157785ada3c3de7f3a1fbd711f8586914f3acf0453"},"schema_version":"1.0","source":{"id":"2306.07929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07929","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07929v2","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07929","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"XGEYBB5IEAFS","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"XGEYBB5IEAFSV5X7","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"XGEYBB5I","created_at":"2026-07-05T07:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:a1e59c00ea07845382d0eb95c46aae41e4ff6087f0d620356f74078744442505","target":"graph","created_at":"2026-07-05T07:06:30Z","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/2306.07929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term experience memory, REMEMBERER is capable of exploiting the experiences from the past episodes even for different task goals, which excels an LLM-based agent with fixed exemplars or equipped with a transient working memory. We further introduce Reinforcement Learning with Experience Memory (RLEM) to update the memory. Thus, the whole system can learn from the experie","authors_text":"Danyang Zhang, Hongshen Xu, Kai Yu, Lu Chen, Situo Zhang, Zihan Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T08:08:18Z","title":"Large Language Models Are Semi-Parametric Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07929","kind":"arxiv","version":2},"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":"sha256:03c216eff42a33d8b686579dccc303b6717a11e48e3b5615325035be95f468dd","target":"record","created_at":"2026-07-05T07:06:30Z","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":"c3e2cf631c4a86bf072b14490ee085a8e187c252a33a33653acb2f2e6c1a3e1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T08:08:18Z","title_canon_sha256":"137024064bd0682326b7aa157785ada3c3de7f3a1fbd711f8586914f3acf0453"},"schema_version":"1.0","source":{"id":"2306.07929","kind":"arxiv","version":2}},"canonical_sha256":"b9898087a8200b2af6fff07d2f560bce65fe79a2082a2aa7557e0601f6b62b9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9898087a8200b2af6fff07d2f560bce65fe79a2082a2aa7557e0601f6b62b9f","first_computed_at":"2026-07-05T07:06:30.102819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:30.102819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FzDSWW17NnDukfFZbj1qFur5aLXAi2/kqRRUr0IxeecxbaxwMfco9E9l5BCq0QRjxRPNmK3NXe7b+4NL/CUPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:30.103285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03c216eff42a33d8b686579dccc303b6717a11e48e3b5615325035be95f468dd","sha256:a1e59c00ea07845382d0eb95c46aae41e4ff6087f0d620356f74078744442505"],"state_sha256":"23a996cb6ab3453739ec5ee48c466257b5ddb3234bc11509c1dd1955d6252df4"}