{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FRMFM6SNYAZYC4MSSHH6AQXL3I","short_pith_number":"pith:FRMFM6SN","schema_version":"1.0","canonical_sha256":"2c58567a4dc03381719291cfe042ebda31321e840d1786664bf8842d3a61f63c","source":{"kind":"arxiv","id":"2406.12125","version":2},"attestation_state":"computed","paper":{"title":"Efficient Sequential Decision Making with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dingyang Chen, Qi Zhang, Yinglun Zhu","submitted_at":"2024-06-17T22:13:22Z","abstract_excerpt":"This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former approach suffers from the computational burden of gradient updates, and the latter approach does not show promising results. In this paper, we propose a new approach that leverages online model selection algorithms to efficiently incorporate LLMs agents into sequential decision making. Statistically, our approach significantly outperforms both traditional decis"},"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":"2406.12125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T22:13:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f3a6dc5570ae65acac943b3ed3e5a8d5ddff0a59a3c10e3505a37d14090ba7b3","abstract_canon_sha256":"af85a534050fa7eeded83e5b65f4de13890afe34655477b011ad3c0f052968f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:33.482599Z","signature_b64":"A41KGYlF5jeCL53L/77ZDUyUTZrz3Z5LyCMEdxoNf5K8B208pg9sgqjS1V4KfX/HoxgXc2oxxbjprdnM6/QbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c58567a4dc03381719291cfe042ebda31321e840d1786664bf8842d3a61f63c","last_reissued_at":"2026-07-05T11:21:33.482086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:33.482086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Sequential Decision Making with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dingyang Chen, Qi Zhang, Yinglun Zhu","submitted_at":"2024-06-17T22:13:22Z","abstract_excerpt":"This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former approach suffers from the computational burden of gradient updates, and the latter approach does not show promising results. In this paper, we propose a new approach that leverages online model selection algorithms to efficiently incorporate LLMs agents into sequential decision making. Statistically, our approach significantly outperforms both traditional decis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12125","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/2406.12125/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":"2406.12125","created_at":"2026-07-05T11:21:33.482152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12125v2","created_at":"2026-07-05T11:21:33.482152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12125","created_at":"2026-07-05T11:21:33.482152+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRMFM6SNYAZY","created_at":"2026-07-05T11:21:33.482152+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRMFM6SNYAZYC4MS","created_at":"2026-07-05T11:21:33.482152+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRMFM6SN","created_at":"2026-07-05T11:21:33.482152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18597","citing_title":"Latent Action Reparameterization for Efficient Agent Inference","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05859","citing_title":"When Do We Need LLMs? A Diagnostic for Language-Driven Bandits","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I","json":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I.json","graph_json":"https://pith.science/api/pith-number/FRMFM6SNYAZYC4MSSHH6AQXL3I/graph.json","events_json":"https://pith.science/api/pith-number/FRMFM6SNYAZYC4MSSHH6AQXL3I/events.json","paper":"https://pith.science/paper/FRMFM6SN"},"agent_actions":{"view_html":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I","download_json":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I.json","view_paper":"https://pith.science/paper/FRMFM6SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12125&json=true","fetch_graph":"https://pith.science/api/pith-number/FRMFM6SNYAZYC4MSSHH6AQXL3I/graph.json","fetch_events":"https://pith.science/api/pith-number/FRMFM6SNYAZYC4MSSHH6AQXL3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I/action/storage_attestation","attest_author":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I/action/author_attestation","sign_citation":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I/action/citation_signature","submit_replication":"https://pith.science/pith/FRMFM6SNYAZYC4MSSHH6AQXL3I/action/replication_record"}},"created_at":"2026-07-05T11:21:33.482152+00:00","updated_at":"2026-07-05T11:21:33.482152+00:00"}