{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6GLER4ONXYI5EPPOR3LFIDYVHA","short_pith_number":"pith:6GLER4ON","schema_version":"1.0","canonical_sha256":"f19648f1cdbe11d23dee8ed6540f15380cb0c8cbdb83d299ad31eee4dccea166","source":{"kind":"arxiv","id":"2603.00026","version":2},"attestation_state":"computed","paper":{"title":"ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengyuan Yang, Wei Hu, Xiaohui Zhang, Yaqin Jin, Yazhong Zhang, Zequn Sun","submitted_at":"2026-02-04T00:54:53Z","abstract_excerpt":"Memory management is essential for LLM agents in long-term interactions. Current memory frameworks typically treat agents as passive ``recorders'' and retrieve information without understanding its deeper implications. They may fail in scenarios requiring reasoning and complex decision-making. To bridge this critical gap, we propose a novel actionable memory framework called ActMem that integrates memory retrieval with active causal reasoning. ActMem transforms unstructured dialogue history into a structured causal and semantic graph. By leveraging counterfactual reasoning and commonsense comp"},"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":"2603.00026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-04T00:54:53Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"c48537e0a935d99d2dd9bde3febcca98bc27a949a5ef1f261e43a1485aad192b","abstract_canon_sha256":"403cd0221912d55e4bf5fb1e29373c6a8811afd4456abdde4dd19e3e5d94e07f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:21.365751Z","signature_b64":"945CR+Wp0Vj/qGuZSfLVAaElrp6+Hdf9aClzR7JE2VKBoBsqnToPTIP+yfvnBUIhu0y30MiCH291gh+BHBZNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f19648f1cdbe11d23dee8ed6540f15380cb0c8cbdb83d299ad31eee4dccea166","last_reissued_at":"2026-06-19T16:11:21.365256Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:21.365256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengyuan Yang, Wei Hu, Xiaohui Zhang, Yaqin Jin, Yazhong Zhang, Zequn Sun","submitted_at":"2026-02-04T00:54:53Z","abstract_excerpt":"Memory management is essential for LLM agents in long-term interactions. Current memory frameworks typically treat agents as passive ``recorders'' and retrieve information without understanding its deeper implications. They may fail in scenarios requiring reasoning and complex decision-making. To bridge this critical gap, we propose a novel actionable memory framework called ActMem that integrates memory retrieval with active causal reasoning. ActMem transforms unstructured dialogue history into a structured causal and semantic graph. By leveraging counterfactual reasoning and commonsense comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00026","kind":"arxiv","version":2},"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/2603.00026/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":"2603.00026","created_at":"2026-06-19T16:11:21.365331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00026v2","created_at":"2026-06-19T16:11:21.365331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00026","created_at":"2026-06-19T16:11:21.365331+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GLER4ONXYI5","created_at":"2026-06-19T16:11:21.365331+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GLER4ONXYI5EPPO","created_at":"2026-06-19T16:11:21.365331+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GLER4ON","created_at":"2026-06-19T16:11:21.365331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.03354","citing_title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA","json":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA.json","graph_json":"https://pith.science/api/pith-number/6GLER4ONXYI5EPPOR3LFIDYVHA/graph.json","events_json":"https://pith.science/api/pith-number/6GLER4ONXYI5EPPOR3LFIDYVHA/events.json","paper":"https://pith.science/paper/6GLER4ON"},"agent_actions":{"view_html":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA","download_json":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA.json","view_paper":"https://pith.science/paper/6GLER4ON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00026&json=true","fetch_graph":"https://pith.science/api/pith-number/6GLER4ONXYI5EPPOR3LFIDYVHA/graph.json","fetch_events":"https://pith.science/api/pith-number/6GLER4ONXYI5EPPOR3LFIDYVHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA/action/storage_attestation","attest_author":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA/action/author_attestation","sign_citation":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA/action/citation_signature","submit_replication":"https://pith.science/pith/6GLER4ONXYI5EPPOR3LFIDYVHA/action/replication_record"}},"created_at":"2026-06-19T16:11:21.365331+00:00","updated_at":"2026-06-19T16:11:21.365331+00:00"}