{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2FJ3VH5CWFXT7TYMHL5ZMPHNNP","short_pith_number":"pith:2FJ3VH5C","schema_version":"1.0","canonical_sha256":"d153ba9fa2b16f3fcf0c3afb963ced6befa3888260de067ac163fc4b4b051aa5","source":{"kind":"arxiv","id":"2502.06975","version":1},"attestation_state":"computed","paper":{"title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Huth, Javier Turek, Jianing Mu, Mariya Toneva, Mathis Pink, Qinyuan Wu, Vy Ai Vo","submitted_at":"2025-02-10T19:14:51Z","abstract_excerpt":"As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological systems solve these challenges with episodic memory, which supports single-shot learning of instance-specific contexts. Inspired by this, we present an episodic memory framework for LLM agents, centered around five key properties of episodic memory that underlie adaptive and context-sensitive behavior. With various research efforts already partially covering these"},"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":"2502.06975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T19:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"429c59b2f49f083c8a6d7f24de1b2fd62d09b0949bf75d806a1ceb25ebc996ab","abstract_canon_sha256":"89bae49d09faab63e1c8e8e9aa317d3a2fc37550f1ff1a5661e5ad543bd692b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:30.948883Z","signature_b64":"mirIpfhVhldvcNhMy4SZZphYSVobZMt+exXG2bMn/ohvxPkSGv1m/1s2xHWs/5zI8a4gNLUHtyTiIR3p0d0dBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d153ba9fa2b16f3fcf0c3afb963ced6befa3888260de067ac163fc4b4b051aa5","last_reissued_at":"2026-07-05T10:12:30.948407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:30.948407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Huth, Javier Turek, Jianing Mu, Mariya Toneva, Mathis Pink, Qinyuan Wu, Vy Ai Vo","submitted_at":"2025-02-10T19:14:51Z","abstract_excerpt":"As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological systems solve these challenges with episodic memory, which supports single-shot learning of instance-specific contexts. Inspired by this, we present an episodic memory framework for LLM agents, centered around five key properties of episodic memory that underlie adaptive and context-sensitive behavior. With various research efforts already partially covering these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06975","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/2502.06975/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":"2502.06975","created_at":"2026-07-05T10:12:30.948460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06975v1","created_at":"2026-07-05T10:12:30.948460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06975","created_at":"2026-07-05T10:12:30.948460+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FJ3VH5CWFXT","created_at":"2026-07-05T10:12:30.948460+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FJ3VH5CWFXT7TYM","created_at":"2026-07-05T10:12:30.948460+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FJ3VH5C","created_at":"2026-07-05T10:12:30.948460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00832","citing_title":"Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12572","citing_title":"LMEB: Long-horizon Memory Embedding Benchmark","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07957","citing_title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00356","citing_title":"MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22085","citing_title":"Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17658","citing_title":"Towards Self-Improving Error Diagnosis in Multi-Agent Systems","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP","json":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP.json","graph_json":"https://pith.science/api/pith-number/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/graph.json","events_json":"https://pith.science/api/pith-number/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/events.json","paper":"https://pith.science/paper/2FJ3VH5C"},"agent_actions":{"view_html":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP","download_json":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP.json","view_paper":"https://pith.science/paper/2FJ3VH5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06975&json=true","fetch_graph":"https://pith.science/api/pith-number/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/graph.json","fetch_events":"https://pith.science/api/pith-number/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/action/storage_attestation","attest_author":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/action/author_attestation","sign_citation":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/action/citation_signature","submit_replication":"https://pith.science/pith/2FJ3VH5CWFXT7TYMHL5ZMPHNNP/action/replication_record"}},"created_at":"2026-07-05T10:12:30.948460+00:00","updated_at":"2026-07-05T10:12:30.948460+00:00"}