{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LVSB5LSLQ3564O4Q7WAS7TVVXQ","short_pith_number":"pith:LVSB5LSL","schema_version":"1.0","canonical_sha256":"5d641eae4b86fbee3b90fd812fceb5bc0fba9d8e7e0f130e66b34542f2090f69","source":{"kind":"arxiv","id":"2506.19652","version":2},"attestation_state":"computed","paper":{"title":"Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Catherine Pelachaud, Florian Pecune, Lucie Galland","submitted_at":"2025-06-24T14:15:26Z","abstract_excerpt":"In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming t"},"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":"2506.19652","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T14:15:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a99ff263a62aa080bcae9b917025eeae77eb64a7fee6f1bf3c6aa079a70391a","abstract_canon_sha256":"b547074e062d37c840ef2d6aa5c1abad871557f6af1fddcbd395cf28be5a9c23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:25.270304Z","signature_b64":"0weAiET3g7LWl8zODbeq1m/KSBasZ6SuuGMLfo+zg0XPPIt4aMPjprgmd/RPlMOfRwyCKaItsYN845HxhM4PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d641eae4b86fbee3b90fd812fceb5bc0fba9d8e7e0f130e66b34542f2090f69","last_reissued_at":"2026-07-05T11:33:25.269822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:25.269822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Catherine Pelachaud, Florian Pecune, Lucie Galland","submitted_at":"2025-06-24T14:15:26Z","abstract_excerpt":"In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19652","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/2506.19652/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":"2506.19652","created_at":"2026-07-05T11:33:25.269877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19652v2","created_at":"2026-07-05T11:33:25.269877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19652","created_at":"2026-07-05T11:33:25.269877+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVSB5LSLQ356","created_at":"2026-07-05T11:33:25.269877+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVSB5LSLQ3564O4Q","created_at":"2026-07-05T11:33:25.269877+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVSB5LSL","created_at":"2026-07-05T11:33:25.269877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28526","citing_title":"A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05345","citing_title":"Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ","json":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ.json","graph_json":"https://pith.science/api/pith-number/LVSB5LSLQ3564O4Q7WAS7TVVXQ/graph.json","events_json":"https://pith.science/api/pith-number/LVSB5LSLQ3564O4Q7WAS7TVVXQ/events.json","paper":"https://pith.science/paper/LVSB5LSL"},"agent_actions":{"view_html":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ","download_json":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ.json","view_paper":"https://pith.science/paper/LVSB5LSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19652&json=true","fetch_graph":"https://pith.science/api/pith-number/LVSB5LSLQ3564O4Q7WAS7TVVXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LVSB5LSLQ3564O4Q7WAS7TVVXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ/action/storage_attestation","attest_author":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ/action/author_attestation","sign_citation":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ/action/citation_signature","submit_replication":"https://pith.science/pith/LVSB5LSLQ3564O4Q7WAS7TVVXQ/action/replication_record"}},"created_at":"2026-07-05T11:33:25.269877+00:00","updated_at":"2026-07-05T11:33:25.269877+00:00"}