{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4QCFFNIT7YFORA47YNG5KWMDVU","short_pith_number":"pith:4QCFFNIT","schema_version":"1.0","canonical_sha256":"e40452b513fe0ae8839fc34dd55983ad2f6ee5314715766ef179a7767f207aa2","source":{"kind":"arxiv","id":"2507.05330","version":1},"attestation_state":"computed","paper":{"title":"MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenghan Yang, Haoxin Wang, Ling Jiang, Ming Gong, Xianhan Peng, Xucheng Huang, Yang Liu","submitted_at":"2025-07-07T17:53:55Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled new applications in e-commerce customer service. However, their capabilities remain constrained in complex, multimodal scenarios. We present MindFlow, the first open-source multimodal LLM agent tailored for e-commerce. Built on the CoALA framework, it integrates memory, decision-making, and action modules, and adopts a modular \"MLLM-as-Tool\" strategy for effect visual-textual reasoning. Evaluated via online A/B testing and simulation-based ablation, MindFlow demonstrates substantial gains in handling complex queries, improving user s"},"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":"2507.05330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T17:53:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a308011de25b5e519f657125a0ab11af7969956e7714d272876b31ff31566df","abstract_canon_sha256":"3882330d670eea513209f6bf230d3fed7c0929b04a8a524b5c7ff07db240026f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:28.448528Z","signature_b64":"OLqDtX21x2JGSEICBIusOpb3Ln+/ROURtvRGm7kCEAXshIrEWf7hui5Q0Y6jGPbnyfJ1tsPyFelfTaZJl+vyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e40452b513fe0ae8839fc34dd55983ad2f6ee5314715766ef179a7767f207aa2","last_reissued_at":"2026-07-05T11:33:28.447927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:28.447927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenghan Yang, Haoxin Wang, Ling Jiang, Ming Gong, Xianhan Peng, Xucheng Huang, Yang Liu","submitted_at":"2025-07-07T17:53:55Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled new applications in e-commerce customer service. However, their capabilities remain constrained in complex, multimodal scenarios. We present MindFlow, the first open-source multimodal LLM agent tailored for e-commerce. Built on the CoALA framework, it integrates memory, decision-making, and action modules, and adopts a modular \"MLLM-as-Tool\" strategy for effect visual-textual reasoning. Evaluated via online A/B testing and simulation-based ablation, MindFlow demonstrates substantial gains in handling complex queries, improving user s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05330","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/2507.05330/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":"2507.05330","created_at":"2026-07-05T11:33:28.447986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05330v1","created_at":"2026-07-05T11:33:28.447986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05330","created_at":"2026-07-05T11:33:28.447986+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QCFFNIT7YFO","created_at":"2026-07-05T11:33:28.447986+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QCFFNIT7YFORA47","created_at":"2026-07-05T11:33:28.447986+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QCFFNIT","created_at":"2026-07-05T11:33:28.447986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30602","citing_title":"MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU","json":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU.json","graph_json":"https://pith.science/api/pith-number/4QCFFNIT7YFORA47YNG5KWMDVU/graph.json","events_json":"https://pith.science/api/pith-number/4QCFFNIT7YFORA47YNG5KWMDVU/events.json","paper":"https://pith.science/paper/4QCFFNIT"},"agent_actions":{"view_html":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU","download_json":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU.json","view_paper":"https://pith.science/paper/4QCFFNIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05330&json=true","fetch_graph":"https://pith.science/api/pith-number/4QCFFNIT7YFORA47YNG5KWMDVU/graph.json","fetch_events":"https://pith.science/api/pith-number/4QCFFNIT7YFORA47YNG5KWMDVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU/action/storage_attestation","attest_author":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU/action/author_attestation","sign_citation":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU/action/citation_signature","submit_replication":"https://pith.science/pith/4QCFFNIT7YFORA47YNG5KWMDVU/action/replication_record"}},"created_at":"2026-07-05T11:33:28.447986+00:00","updated_at":"2026-07-05T11:33:28.447986+00:00"}