{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22VQNQKP5GPBNQKFARD2Y4AQPF","short_pith_number":"pith:22VQNQKP","schema_version":"1.0","canonical_sha256":"d6ab06c14fe99e16c1450447ac70107948b50de356ca55d82c90c165f28722eb","source":{"kind":"arxiv","id":"2404.07456","version":1},"attestation_state":"computed","paper":{"title":"WESE: Weak Exploration to Strong Exploitation for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Defu Lian, Enhong Chen, Ruiming Tang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Xu Huang, Yasheng Wang","submitted_at":"2024-04-11T03:31:54Z","abstract_excerpt":"Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt engineering or task-specific fine-tuning, ignoring the procedure of exploration and exploitation. When addressing complex tasks within open-world interactive environments, these methods exhibit limitations. Firstly, the lack of global information of environments leads to greedy decisions, resulting in sub-optimal solutions. On the other hand, irrelevant inform"},"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":"2404.07456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-11T03:31:54Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"78b78237c9b054b068e4903def5a1f8d9f93389b13768e4974503fee4f01c01f","abstract_canon_sha256":"7bb7c3f306863d3602bbf421fda7e538ee6b7fc258581bebcca64608f0c2218e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:53.215543Z","signature_b64":"0cOc1+1DwMC35QLwXv4MByLKwwVZyKGRf6MMJss7UTDJTV9cYOBT9wNLfCQCPYaTwpvrTvnLsjdq027xWDJtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6ab06c14fe99e16c1450447ac70107948b50de356ca55d82c90c165f28722eb","last_reissued_at":"2026-07-05T08:06:53.215122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:53.215122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WESE: Weak Exploration to Strong Exploitation for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Defu Lian, Enhong Chen, Ruiming Tang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Xu Huang, Yasheng Wang","submitted_at":"2024-04-11T03:31:54Z","abstract_excerpt":"Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt engineering or task-specific fine-tuning, ignoring the procedure of exploration and exploitation. When addressing complex tasks within open-world interactive environments, these methods exhibit limitations. Firstly, the lack of global information of environments leads to greedy decisions, resulting in sub-optimal solutions. On the other hand, irrelevant inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07456","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/2404.07456/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":"2404.07456","created_at":"2026-07-05T08:06:53.215179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07456v1","created_at":"2026-07-05T08:06:53.215179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07456","created_at":"2026-07-05T08:06:53.215179+00:00"},{"alias_kind":"pith_short_12","alias_value":"22VQNQKP5GPB","created_at":"2026-07-05T08:06:53.215179+00:00"},{"alias_kind":"pith_short_16","alias_value":"22VQNQKP5GPBNQKF","created_at":"2026-07-05T08:06:53.215179+00:00"},{"alias_kind":"pith_short_8","alias_value":"22VQNQKP","created_at":"2026-07-05T08:06:53.215179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF","json":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF.json","graph_json":"https://pith.science/api/pith-number/22VQNQKP5GPBNQKFARD2Y4AQPF/graph.json","events_json":"https://pith.science/api/pith-number/22VQNQKP5GPBNQKFARD2Y4AQPF/events.json","paper":"https://pith.science/paper/22VQNQKP"},"agent_actions":{"view_html":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF","download_json":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF.json","view_paper":"https://pith.science/paper/22VQNQKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07456&json=true","fetch_graph":"https://pith.science/api/pith-number/22VQNQKP5GPBNQKFARD2Y4AQPF/graph.json","fetch_events":"https://pith.science/api/pith-number/22VQNQKP5GPBNQKFARD2Y4AQPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF/action/storage_attestation","attest_author":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF/action/author_attestation","sign_citation":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF/action/citation_signature","submit_replication":"https://pith.science/pith/22VQNQKP5GPBNQKFARD2Y4AQPF/action/replication_record"}},"created_at":"2026-07-05T08:06:53.215179+00:00","updated_at":"2026-07-05T08:06:53.215179+00:00"}