{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KJ7ZU2OJ62XNSL5HWGKO7BEFFK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0baa9238b792d9636e43af4ee7fc3d7dd5e814b373f47c0acbfc7262cfe7cc02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T09:22:39Z","title_canon_sha256":"1cb6e671c818d0b61536f0b5d79b788a0a58b9972247a60715f8589ff4c5c957"},"schema_version":"1.0","source":{"id":"2502.00728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00728","created_at":"2026-07-05T10:08:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00728v1","created_at":"2026-07-05T10:08:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00728","created_at":"2026-07-05T10:08:37Z"},{"alias_kind":"pith_short_12","alias_value":"KJ7ZU2OJ62XN","created_at":"2026-07-05T10:08:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJ7ZU2OJ62XNSL5H","created_at":"2026-07-05T10:08:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJ7ZU2OJ","created_at":"2026-07-05T10:08:37Z"}],"graph_snapshots":[{"event_id":"sha256:41918a827ac0710087d4ca263488141e15f09a5ed832a79371b8c1a85ced6900","target":"graph","created_at":"2026-07-05T10:08:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.00728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by providing it with a fixed, manually designed meta-prompt. However, numerous previous works have found that the prompt has a significant impact on the performance of the LLM, which calls for a method to automatically optimize the meta-prompt for LLM-based agents. Unfortunately, the non-stationarity in the reward observations during LLM-based sequential decision","authors_text":"Mingze Kong, Yao Shu, Zhiyong Wang, Zhongxiang Dai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00728","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:417df892d49621b6ca3dffcd888964d4a90e07f22d45ddedbd93cb4184184649","target":"record","created_at":"2026-07-05T10:08:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0baa9238b792d9636e43af4ee7fc3d7dd5e814b373f47c0acbfc7262cfe7cc02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T09:22:39Z","title_canon_sha256":"1cb6e671c818d0b61536f0b5d79b788a0a58b9972247a60715f8589ff4c5c957"},"schema_version":"1.0","source":{"id":"2502.00728","kind":"arxiv","version":1}},"canonical_sha256":"527f9a69c9f6aed92fa7b194ef84852ab86a7039458033eb551391e035a6150f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527f9a69c9f6aed92fa7b194ef84852ab86a7039458033eb551391e035a6150f","first_computed_at":"2026-07-05T10:08:37.815517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:37.815517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NmmbRoCFgLvm0th9Lm+JJ5ARl1HnoflYg0KBY2QM4p7680GTtBk7+xB/IbOQxoLLUBVA/cJwXX84ZExOcCDaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:37.815962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:417df892d49621b6ca3dffcd888964d4a90e07f22d45ddedbd93cb4184184649","sha256:41918a827ac0710087d4ca263488141e15f09a5ed832a79371b8c1a85ced6900"],"state_sha256":"bc198a05b75dc9317468c3a1cdccc258b89ebb4ca0d584aa936a89866ea835e3"}