{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZIWRV55Z3LKYNPW3BM2UFE5FAR","short_pith_number":"pith:ZIWRV55Z","schema_version":"1.0","canonical_sha256":"ca2d1af7b9dad586bedb0b354293a50467b7ba698df8019f2e01a7c9f4a199e3","source":{"kind":"arxiv","id":"2605.22240","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Proactivity in Task-Oriented Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingdong Tan, Chaozheng Wang, Hongbin Zhang, Jinpeng Wang, Ning Gao, Rena Wei Gao, Ruiyuan Wu, Shuzheng Gao, Yuqin Dai, Zongjie Li","submitted_at":"2026-05-21T09:46:25Z","abstract_excerpt":"Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user's latent concerns unlocks proactive capability that no amount of sampling can undermine, establishing these concerns as a pivotal training-time signal. To operationalize this finding, we bu"},"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":"2605.22240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:46:25Z","cross_cats_sorted":[],"title_canon_sha256":"5edde9e0401071dec1a66e323fd92ca81bc53d01da1197a983e6e19193b66e12","abstract_canon_sha256":"d7c2db9b319acf0f48823fded9703eba678111725ce746de9a075fd3885a9d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:33.866390Z","signature_b64":"aYSY7SFYFLnFq+MLXYatBaG7Zq3SrBWbs4m5akhtYMclE409Tu4rVPw50pDRYT+uIatpan7VttjLdk0HZWPGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca2d1af7b9dad586bedb0b354293a50467b7ba698df8019f2e01a7c9f4a199e3","last_reissued_at":"2026-05-22T01:04:33.865639Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:33.865639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Proactivity in Task-Oriented Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingdong Tan, Chaozheng Wang, Hongbin Zhang, Jinpeng Wang, Ning Gao, Rena Wei Gao, Ruiyuan Wu, Shuzheng Gao, Yuqin Dai, Zongjie Li","submitted_at":"2026-05-21T09:46:25Z","abstract_excerpt":"Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user's latent concerns unlocks proactive capability that no amount of sampling can undermine, establishing these concerns as a pivotal training-time signal. To operationalize this finding, we bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22240","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/2605.22240/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":"2605.22240","created_at":"2026-05-22T01:04:33.865766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22240v1","created_at":"2026-05-22T01:04:33.865766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22240","created_at":"2026-05-22T01:04:33.865766+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIWRV55Z3LKY","created_at":"2026-05-22T01:04:33.865766+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIWRV55Z3LKYNPW3","created_at":"2026-05-22T01:04:33.865766+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIWRV55Z","created_at":"2026-05-22T01:04:33.865766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR","json":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR.json","graph_json":"https://pith.science/api/pith-number/ZIWRV55Z3LKYNPW3BM2UFE5FAR/graph.json","events_json":"https://pith.science/api/pith-number/ZIWRV55Z3LKYNPW3BM2UFE5FAR/events.json","paper":"https://pith.science/paper/ZIWRV55Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR","download_json":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR.json","view_paper":"https://pith.science/paper/ZIWRV55Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22240&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIWRV55Z3LKYNPW3BM2UFE5FAR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIWRV55Z3LKYNPW3BM2UFE5FAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR/action/storage_attestation","attest_author":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR/action/author_attestation","sign_citation":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR/action/citation_signature","submit_replication":"https://pith.science/pith/ZIWRV55Z3LKYNPW3BM2UFE5FAR/action/replication_record"}},"created_at":"2026-05-22T01:04:33.865766+00:00","updated_at":"2026-05-22T01:04:33.865766+00:00"}