{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ASCLPXVTPRZIFD4I3LGC7RFAUP","short_pith_number":"pith:ASCLPXVT","schema_version":"1.0","canonical_sha256":"0484b7deb37c72828f88dacc2fc4a0a3c8f97cb4abe8c9a96ce910701ba5af3b","source":{"kind":"arxiv","id":"2506.06316","version":1},"attestation_state":"computed","paper":{"title":"A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Haoyang Feng, Yanjun Dai, Yuan Gao","submitted_at":"2025-05-27T03:31:07Z","abstract_excerpt":"For personalized marketing, a new challenge of how to effectively algorithm the A/B testing to maximize user response is urgently to be overcome. In this paper, we present a new approach, the RL-LLM-AB test framework, for using reinforcement learning strategy optimization combined with LLM to automate and personalize A/B tests. The RL-LLM-AB test is built upon the pre-trained instruction-tuned language model. It first generates A/B versions of candidate content variants using a Prompt-Conditioned Generator, and then dynamically embeds and fuses the user portrait and the context of the current "},"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":"2506.06316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T03:31:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c42bcbf40bba17e3290e0ddd4802100e3c44c8a1a56d7f2eda219ac7f1ab2ac","abstract_canon_sha256":"f44991365b1ec5ac5d01c87a70f114d8cc6bf8f49b30bda98c4d1328ed226163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:47.922816Z","signature_b64":"6Pp4rRE/AhPDBiILT+EPGqRIj18A9uv7rMvTB6SXlE5h3sqGu7rvYWFTPnTUpCjDIH2SxLOR7A2djZKdi8EzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0484b7deb37c72828f88dacc2fc4a0a3c8f97cb4abe8c9a96ce910701ba5af3b","last_reissued_at":"2026-07-05T11:17:47.922335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:47.922335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Haoyang Feng, Yanjun Dai, Yuan Gao","submitted_at":"2025-05-27T03:31:07Z","abstract_excerpt":"For personalized marketing, a new challenge of how to effectively algorithm the A/B testing to maximize user response is urgently to be overcome. In this paper, we present a new approach, the RL-LLM-AB test framework, for using reinforcement learning strategy optimization combined with LLM to automate and personalize A/B tests. The RL-LLM-AB test is built upon the pre-trained instruction-tuned language model. It first generates A/B versions of candidate content variants using a Prompt-Conditioned Generator, and then dynamically embeds and fuses the user portrait and the context of the current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06316","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/2506.06316/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":"2506.06316","created_at":"2026-07-05T11:17:47.922392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06316v1","created_at":"2026-07-05T11:17:47.922392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06316","created_at":"2026-07-05T11:17:47.922392+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASCLPXVTPRZI","created_at":"2026-07-05T11:17:47.922392+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASCLPXVTPRZIFD4I","created_at":"2026-07-05T11:17:47.922392+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASCLPXVT","created_at":"2026-07-05T11:17:47.922392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.09721","citing_title":"A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP","json":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP.json","graph_json":"https://pith.science/api/pith-number/ASCLPXVTPRZIFD4I3LGC7RFAUP/graph.json","events_json":"https://pith.science/api/pith-number/ASCLPXVTPRZIFD4I3LGC7RFAUP/events.json","paper":"https://pith.science/paper/ASCLPXVT"},"agent_actions":{"view_html":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP","download_json":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP.json","view_paper":"https://pith.science/paper/ASCLPXVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06316&json=true","fetch_graph":"https://pith.science/api/pith-number/ASCLPXVTPRZIFD4I3LGC7RFAUP/graph.json","fetch_events":"https://pith.science/api/pith-number/ASCLPXVTPRZIFD4I3LGC7RFAUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP/action/storage_attestation","attest_author":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP/action/author_attestation","sign_citation":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP/action/citation_signature","submit_replication":"https://pith.science/pith/ASCLPXVTPRZIFD4I3LGC7RFAUP/action/replication_record"}},"created_at":"2026-07-05T11:17:47.922392+00:00","updated_at":"2026-07-05T11:17:47.922392+00:00"}