{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XUPFW3WEZTIM5Y5LGGFW2U4ZVT","short_pith_number":"pith:XUPFW3WE","schema_version":"1.0","canonical_sha256":"bd1e5b6ec4ccd0cee3ab318b6d5399ace412671b8c6c76974e59f88822cca5cb","source":{"kind":"arxiv","id":"2309.17382","version":3},"attestation_state":"computed","paper":{"title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Boyi Liu, Hao Hu, Hongyi Guo, Shenao Zhang, Shuqi Ke, Zhaoran Wang, Zhihan Liu","submitted_at":"2023-09-29T16:36:39Z","abstract_excerpt":"Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it remains unclear how to complete a given task provably within a minimum number of interactions with the external environment, e.g., through an internal mechanism of reasoning. To this end, we propose a principled framework with provable regret guarantees to orchestrate reasoning and acting, which we call \"reason for future, act for now\" (\\texttt{RAFA}). Specifically, we design a prompt template for reasoning that learns from the"},"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":"2309.17382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-09-29T16:36:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b742498cbb730f85523e36e6113a5d6a029e2e4296ad46488d06aa73d9ff13b","abstract_canon_sha256":"b080a5808735da510c61ea28559f7aaf189bbae962f550d8c8f7a720ceeb57bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:34.564822Z","signature_b64":"X20kAyGtK+I8vvKsDj0Zamj+6fRffTIEujrtAphdF89AdVq2KUOC6DHv9Q0mSAVZNLhiiaXOfGYnpQnoCtzLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1e5b6ec4ccd0cee3ab318b6d5399ace412671b8c6c76974e59f88822cca5cb","last_reissued_at":"2026-07-05T08:38:34.564418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:34.564418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Boyi Liu, Hao Hu, Hongyi Guo, Shenao Zhang, Shuqi Ke, Zhaoran Wang, Zhihan Liu","submitted_at":"2023-09-29T16:36:39Z","abstract_excerpt":"Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it remains unclear how to complete a given task provably within a minimum number of interactions with the external environment, e.g., through an internal mechanism of reasoning. To this end, we propose a principled framework with provable regret guarantees to orchestrate reasoning and acting, which we call \"reason for future, act for now\" (\\texttt{RAFA}). Specifically, we design a prompt template for reasoning that learns from the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17382","kind":"arxiv","version":3},"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/2309.17382/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":"2309.17382","created_at":"2026-07-05T08:38:34.564477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17382v3","created_at":"2026-07-05T08:38:34.564477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17382","created_at":"2026-07-05T08:38:34.564477+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUPFW3WEZTIM","created_at":"2026-07-05T08:38:34.564477+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUPFW3WEZTIM5Y5L","created_at":"2026-07-05T08:38:34.564477+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUPFW3WE","created_at":"2026-07-05T08:38:34.564477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2310.04406","citing_title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12755","citing_title":"State-Centric Decision Process","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT","json":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT.json","graph_json":"https://pith.science/api/pith-number/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/graph.json","events_json":"https://pith.science/api/pith-number/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/events.json","paper":"https://pith.science/paper/XUPFW3WE"},"agent_actions":{"view_html":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT","download_json":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT.json","view_paper":"https://pith.science/paper/XUPFW3WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17382&json=true","fetch_graph":"https://pith.science/api/pith-number/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/graph.json","fetch_events":"https://pith.science/api/pith-number/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/action/storage_attestation","attest_author":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/action/author_attestation","sign_citation":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/action/citation_signature","submit_replication":"https://pith.science/pith/XUPFW3WEZTIM5Y5LGGFW2U4ZVT/action/replication_record"}},"created_at":"2026-07-05T08:38:34.564477+00:00","updated_at":"2026-07-05T08:38:34.564477+00:00"}