{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7GYTYXCZINHO3FIRS5UGUUW5U6","short_pith_number":"pith:7GYTYXCZ","schema_version":"1.0","canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","source":{"kind":"arxiv","id":"2605.14553","version":1},"attestation_state":"computed","paper":{"title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengshuai Shi, Cong Shen, Donghao Li, Jing Yang, Weijuan Ou","submitted_at":"2026-05-14T08:31:17Z","abstract_excerpt":"Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt p"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c149f0a446ae0b8ac99743af2877fb60c45c6e55da7fa3e0aad129f942dc622","abstract_canon_sha256":"f050c93ebd59f08f662dc444c16665764f030df1eef20bb1bde6cb98a3ae691b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.682736Z","signature_b64":"he57Oo1NPBwiXG6PDg4uqtqbghRbY4mlJ6znf7Mu2B13nneMiP7Z8NMGlu374Bcf5JK2j//Tf081f1nfuA3sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","last_reissued_at":"2026-05-17T23:39:05.682032Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.682032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengshuai Shi, Cong Shen, Donghao Li, Jing Yang, Weijuan Ou","submitted_at":"2026-05-14T08:31:17Z","abstract_excerpt":"Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c558920ac2ac792c7247d4fc736c4717fb47f4e8affad22e63b6cedd3eccd3f1"},"source":{"id":"2605.14553","kind":"arxiv","version":1},"verdict":{"id":"ae9d7599-fe60-4212-afc9-226b40e7a23c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:47:29.025982Z","strongest_claim":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines.","one_line_summary":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity.","pith_extraction_headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees."},"references":{"count":33,"sample":[{"doi":"","year":2025,"title":"Gepa: Reflective prompt evolution can outperform reinforcement learning","work_id":"3de5a529-96e4-4800-82cd-546562b68f98","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Best arm identification in multi-armed bandits","work_id":"8c40c1c5-f69c-4f4d-966c-e335bdb85b4e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901","work_id":"84780adb-76cf-44ac-a8b7-e24d4fa5c592","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Leaf: A benchmark for federated settings","work_id":"94ec8be1-6cf1-4962-994c-e762a0b9c3ee","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Discrete prompt optimization via constrained generation for zero-shot re-ranker","work_id":"0c01ab93-25b2-4bca-b51b-919144ac6c2c","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"9a0161828a6a59d6c66ffc98eb97c27ce3a8e511285d867ad587ec3324b600cd","internal_anchors":4},"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":"2605.14553","created_at":"2026-05-17T23:39:05.682148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14553v1","created_at":"2026-05-17T23:39:05.682148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14553","created_at":"2026-05-17T23:39:05.682148+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GYTYXCZINHO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GYTYXCZINHO3FIR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GYTYXCZ","created_at":"2026-05-18T12:33:37.589309+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/7GYTYXCZINHO3FIRS5UGUUW5U6","json":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6.json","graph_json":"https://pith.science/api/pith-number/7GYTYXCZINHO3FIRS5UGUUW5U6/graph.json","events_json":"https://pith.science/api/pith-number/7GYTYXCZINHO3FIRS5UGUUW5U6/events.json","paper":"https://pith.science/paper/7GYTYXCZ"},"agent_actions":{"view_html":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6","download_json":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6.json","view_paper":"https://pith.science/paper/7GYTYXCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14553&json=true","fetch_graph":"https://pith.science/api/pith-number/7GYTYXCZINHO3FIRS5UGUUW5U6/graph.json","fetch_events":"https://pith.science/api/pith-number/7GYTYXCZINHO3FIRS5UGUUW5U6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/action/storage_attestation","attest_author":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/action/author_attestation","sign_citation":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/action/citation_signature","submit_replication":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/action/replication_record"}},"created_at":"2026-05-17T23:39:05.682148+00:00","updated_at":"2026-05-17T23:39:05.682148+00:00"}