{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXZBDZZJ2XWYDUUG32B4234A32","short_pith_number":"pith:DXZBDZZJ","schema_version":"1.0","canonical_sha256":"1df211e729d5ed81d286de83cd6f80de85623be1cb3dacf777cb990f0b4d6cb7","source":{"kind":"arxiv","id":"2401.02777","version":2},"attestation_state":"computed","paper":{"title":"From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaijiang Chen, Liangyu Chen, Ming Cui, Na Liu, Wei Zou, Xiaoyu Tian","submitted_at":"2024-01-05T12:26:46Z","abstract_excerpt":"This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents. RAISE, an enhancement of the ReAct framework, incorporates a dual-component memory system, mirroring human short-term and long-term memory, to maintain context and continuity in conversations. It entails a comprehensive agent construction scenario, including phases like Conversation Selection, Scene Extraction, CoT Completion, and Scene Augmentation, leading to the LLMs Training phase. This "},"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":"2401.02777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-05T12:26:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b7dc780a8f98be83082162e4df2bb2c176e49d28765099458768c0a0546cea7","abstract_canon_sha256":"f27d503b96380a2d8717eb0a1ab78bbe781bc6dbb31489c2674ed604c0aca495"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:53.947660Z","signature_b64":"F5M1GVp30G4inHZ1UwsJaEQIjjYqLbwpeBwCqxfV+y7DZazImGXSJOxpdOpA0LgX5R45atHA9cs2LUtdSOCKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df211e729d5ed81d286de83cd6f80de85623be1cb3dacf777cb990f0b4d6cb7","last_reissued_at":"2026-07-05T07:38:53.947156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:53.947156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaijiang Chen, Liangyu Chen, Ming Cui, Na Liu, Wei Zou, Xiaoyu Tian","submitted_at":"2024-01-05T12:26:46Z","abstract_excerpt":"This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents. RAISE, an enhancement of the ReAct framework, incorporates a dual-component memory system, mirroring human short-term and long-term memory, to maintain context and continuity in conversations. It entails a comprehensive agent construction scenario, including phases like Conversation Selection, Scene Extraction, CoT Completion, and Scene Augmentation, leading to the LLMs Training phase. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02777","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/2401.02777/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":"2401.02777","created_at":"2026-07-05T07:38:53.947213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02777v2","created_at":"2026-07-05T07:38:53.947213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02777","created_at":"2026-07-05T07:38:53.947213+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXZBDZZJ2XWY","created_at":"2026-07-05T07:38:53.947213+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXZBDZZJ2XWYDUUG","created_at":"2026-07-05T07:38:53.947213+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXZBDZZJ","created_at":"2026-07-05T07:38:53.947213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.11584","citing_title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11628","citing_title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18375","citing_title":"IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32","json":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32.json","graph_json":"https://pith.science/api/pith-number/DXZBDZZJ2XWYDUUG32B4234A32/graph.json","events_json":"https://pith.science/api/pith-number/DXZBDZZJ2XWYDUUG32B4234A32/events.json","paper":"https://pith.science/paper/DXZBDZZJ"},"agent_actions":{"view_html":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32","download_json":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32.json","view_paper":"https://pith.science/paper/DXZBDZZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02777&json=true","fetch_graph":"https://pith.science/api/pith-number/DXZBDZZJ2XWYDUUG32B4234A32/graph.json","fetch_events":"https://pith.science/api/pith-number/DXZBDZZJ2XWYDUUG32B4234A32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32/action/storage_attestation","attest_author":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32/action/author_attestation","sign_citation":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32/action/citation_signature","submit_replication":"https://pith.science/pith/DXZBDZZJ2XWYDUUG32B4234A32/action/replication_record"}},"created_at":"2026-07-05T07:38:53.947213+00:00","updated_at":"2026-07-05T07:38:53.947213+00:00"}