{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7F36AYDPEZNVYHPQBR36D7B7RF","short_pith_number":"pith:7F36AYDP","schema_version":"1.0","canonical_sha256":"f977e0606f265b5c1df00c77e1fc3f894d3cc94cd7d029d4b4331295009e6b54","source":{"kind":"arxiv","id":"2507.18884","version":1},"attestation_state":"computed","paper":{"title":"MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Gong, Vijayan K. Asari, Xucheng Huang, Ziheng Xu","submitted_at":"2025-07-25T02:01:55Z","abstract_excerpt":"High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-evolving dialogue agent that learns domain-specific behavior by combining large language models (LLMs) with imitation learning and offline reinforcement learning (RL). MindFlow+ introduces two data-centric mechanisms to guide learning: tool-augmented demonstration construction, which exposes the model to knowledge-enhanced and agentic (ReAct-style) interactions for effective tool use; and reward-conditioned data mode"},"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":"2507.18884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T02:01:55Z","cross_cats_sorted":[],"title_canon_sha256":"748d98853be3e3cbd348d50232f2f1a0eafa12a4945302cc64f769e281e1f334","abstract_canon_sha256":"56d6102d58b70dd550fa5bc8f762940c5892a549a607b5c30ada40b5867cfa3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:15.421833Z","signature_b64":"H89ldx5sA1l2Ov4jM2HdSlImCBghAAQ2YM721ub3IQ4YGCtUIAyuQKxW8CBmuq+VTKEHBpU2zhAOzpaA+RkPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f977e0606f265b5c1df00c77e1fc3f894d3cc94cd7d029d4b4331295009e6b54","last_reissued_at":"2026-07-05T11:43:15.421387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:15.421387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Gong, Vijayan K. Asari, Xucheng Huang, Ziheng Xu","submitted_at":"2025-07-25T02:01:55Z","abstract_excerpt":"High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-evolving dialogue agent that learns domain-specific behavior by combining large language models (LLMs) with imitation learning and offline reinforcement learning (RL). MindFlow+ introduces two data-centric mechanisms to guide learning: tool-augmented demonstration construction, which exposes the model to knowledge-enhanced and agentic (ReAct-style) interactions for effective tool use; and reward-conditioned data mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18884","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/2507.18884/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":"2507.18884","created_at":"2026-07-05T11:43:15.421445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18884v1","created_at":"2026-07-05T11:43:15.421445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18884","created_at":"2026-07-05T11:43:15.421445+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F36AYDPEZNV","created_at":"2026-07-05T11:43:15.421445+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F36AYDPEZNVYHPQ","created_at":"2026-07-05T11:43:15.421445+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F36AYDP","created_at":"2026-07-05T11:43:15.421445+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/7F36AYDPEZNVYHPQBR36D7B7RF","json":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF.json","graph_json":"https://pith.science/api/pith-number/7F36AYDPEZNVYHPQBR36D7B7RF/graph.json","events_json":"https://pith.science/api/pith-number/7F36AYDPEZNVYHPQBR36D7B7RF/events.json","paper":"https://pith.science/paper/7F36AYDP"},"agent_actions":{"view_html":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF","download_json":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF.json","view_paper":"https://pith.science/paper/7F36AYDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18884&json=true","fetch_graph":"https://pith.science/api/pith-number/7F36AYDPEZNVYHPQBR36D7B7RF/graph.json","fetch_events":"https://pith.science/api/pith-number/7F36AYDPEZNVYHPQBR36D7B7RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF/action/storage_attestation","attest_author":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF/action/author_attestation","sign_citation":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF/action/citation_signature","submit_replication":"https://pith.science/pith/7F36AYDPEZNVYHPQBR36D7B7RF/action/replication_record"}},"created_at":"2026-07-05T11:43:15.421445+00:00","updated_at":"2026-07-05T11:43:15.421445+00:00"}