{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PX3X4PXSCBAZWB53SAHANZOTRZ","short_pith_number":"pith:PX3X4PXS","schema_version":"1.0","canonical_sha256":"7df77e3ef210419b07bb900e06e5d38e65b317d2a4073a87639ae84cf1629736","source":{"kind":"arxiv","id":"2506.06254","version":2},"attestation_state":"computed","paper":{"title":"PersonaAgent: Bridging Memory and Action for Personalized LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenwei Zhang, Henry Peng Zou, Jingbo Shang, Jingguo Liu, Liangwei Yang, Lian Xiong, Philip S. Yu, Weizhi Zhang, Xian Li, Xiaoman Pan, Xinyang Zhang, Yifan Gao, Zhengyang Wang, Zhepei Wei, Zijie Huang","submitted_at":"2025-06-06T17:29:49Z","abstract_excerpt":"Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users' varying needs and preferences. This limitation motivates us to develop PersonaAgent, the first personalized LLM agent framework designed to address versatile personalization tasks. Specifically, PersonaAgent integrates two complementary components - a personalized memory module that includes episodic and "},"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":"2506.06254","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:29:49Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"88bfe6b11aa2e712486d63476126e93f8deb50586cd8d5ccb156068604b96799","abstract_canon_sha256":"716126c9a289c71ff7f3b3c42a492d5f2a57839c027e7e9aa9d226449511ed31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:53.787601Z","signature_b64":"+dCMgNgZx61KfSgL0Gn3pbb7LqgKDkgQMb5vm3mZSnw20dLiSz/1FBotvoy2CzuQ5NApQwaEc34tOfxSTwzMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df77e3ef210419b07bb900e06e5d38e65b317d2a4073a87639ae84cf1629736","last_reissued_at":"2026-05-29T01:04:53.786748Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:53.786748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersonaAgent: Bridging Memory and Action for Personalized LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenwei Zhang, Henry Peng Zou, Jingbo Shang, Jingguo Liu, Liangwei Yang, Lian Xiong, Philip S. Yu, Weizhi Zhang, Xian Li, Xiaoman Pan, Xinyang Zhang, Yifan Gao, Zhengyang Wang, Zhepei Wei, Zijie Huang","submitted_at":"2025-06-06T17:29:49Z","abstract_excerpt":"Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users' varying needs and preferences. This limitation motivates us to develop PersonaAgent, the first personalized LLM agent framework designed to address versatile personalization tasks. Specifically, PersonaAgent integrates two complementary components - a personalized memory module that includes episodic and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06254","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/2506.06254/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":"2506.06254","created_at":"2026-05-29T01:04:53.787128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06254v2","created_at":"2026-05-29T01:04:53.787128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06254","created_at":"2026-05-29T01:04:53.787128+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX3X4PXSCBAZ","created_at":"2026-05-29T01:04:53.787128+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX3X4PXSCBAZWB53","created_at":"2026-05-29T01:04:53.787128+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX3X4PXS","created_at":"2026-05-29T01:04:53.787128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.16551","citing_title":"PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15343","citing_title":"Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27882","citing_title":"Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ","json":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ.json","graph_json":"https://pith.science/api/pith-number/PX3X4PXSCBAZWB53SAHANZOTRZ/graph.json","events_json":"https://pith.science/api/pith-number/PX3X4PXSCBAZWB53SAHANZOTRZ/events.json","paper":"https://pith.science/paper/PX3X4PXS"},"agent_actions":{"view_html":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ","download_json":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ.json","view_paper":"https://pith.science/paper/PX3X4PXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06254&json=true","fetch_graph":"https://pith.science/api/pith-number/PX3X4PXSCBAZWB53SAHANZOTRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PX3X4PXSCBAZWB53SAHANZOTRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ/action/storage_attestation","attest_author":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ/action/author_attestation","sign_citation":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ/action/citation_signature","submit_replication":"https://pith.science/pith/PX3X4PXSCBAZWB53SAHANZOTRZ/action/replication_record"}},"created_at":"2026-05-29T01:04:53.787128+00:00","updated_at":"2026-05-29T01:04:53.787128+00:00"}