{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BXRD33NDVR2Y4DI2NZP7RTL7BT","short_pith_number":"pith:BXRD33ND","schema_version":"1.0","canonical_sha256":"0de23deda3ac758e0d1a6e5ff8cd7f0cc6eacd8bf48a2f15c494bf4ac4ab651b","source":{"kind":"arxiv","id":"2505.16582","version":2},"attestation_state":"computed","paper":{"title":"O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Botian Shi, Chengjun Xie, Daocheng Fu, Jianbiao Mei, Licheng Wen, Pinlong Cai, Rong Wu, Tao Hu, Xing Gao, Xinyu Cai, Xuemeng Yang, Yong Liu, Yu Qiao, Yu Yang","submitted_at":"2025-05-22T12:17:13Z","abstract_excerpt":"Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to-date information. While enabling LLMs to interact with external knowledge environments is a promising solution, current efforts primarily address closed-end problems. Open-ended questions, which characterized by lacking a standard answer or providing non-unique and diverse answers, remain underexplored. To bridge this gap, we present O$^2$-Searcher, a novel search agent leveraging reinforcement learning to effective"},"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":"2505.16582","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:17:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1f0f83cab3927004b281ad59244deaa5aa13c9d516a58f653babe823f0ef58d","abstract_canon_sha256":"13580807a0c15e2cf60a4f868c7d2b775fe60843be10210a265624283b8fb60d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:15.417331Z","signature_b64":"VZGIEg0OantDCKGyRFPX4v1nItUNuYpFIiuWsh5OBFwv+2q/U762RcCPi9+2t2JDSu9XpQXpOQwl8g3CGJjOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de23deda3ac758e0d1a6e5ff8cd7f0cc6eacd8bf48a2f15c494bf4ac4ab651b","last_reissued_at":"2026-07-05T11:09:15.416765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:15.416765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Botian Shi, Chengjun Xie, Daocheng Fu, Jianbiao Mei, Licheng Wen, Pinlong Cai, Rong Wu, Tao Hu, Xing Gao, Xinyu Cai, Xuemeng Yang, Yong Liu, Yu Qiao, Yu Yang","submitted_at":"2025-05-22T12:17:13Z","abstract_excerpt":"Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to-date information. While enabling LLMs to interact with external knowledge environments is a promising solution, current efforts primarily address closed-end problems. Open-ended questions, which characterized by lacking a standard answer or providing non-unique and diverse answers, remain underexplored. To bridge this gap, we present O$^2$-Searcher, a novel search agent leveraging reinforcement learning to effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16582","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/2505.16582/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":"2505.16582","created_at":"2026-07-05T11:09:15.416829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16582v2","created_at":"2026-07-05T11:09:15.416829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16582","created_at":"2026-07-05T11:09:15.416829+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXRD33NDVR2Y","created_at":"2026-07-05T11:09:15.416829+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXRD33NDVR2Y4DI2","created_at":"2026-07-05T11:09:15.416829+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXRD33ND","created_at":"2026-07-05T11:09:15.416829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26122","citing_title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30824","citing_title":"Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00861","citing_title":"Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT","json":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT.json","graph_json":"https://pith.science/api/pith-number/BXRD33NDVR2Y4DI2NZP7RTL7BT/graph.json","events_json":"https://pith.science/api/pith-number/BXRD33NDVR2Y4DI2NZP7RTL7BT/events.json","paper":"https://pith.science/paper/BXRD33ND"},"agent_actions":{"view_html":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT","download_json":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT.json","view_paper":"https://pith.science/paper/BXRD33ND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16582&json=true","fetch_graph":"https://pith.science/api/pith-number/BXRD33NDVR2Y4DI2NZP7RTL7BT/graph.json","fetch_events":"https://pith.science/api/pith-number/BXRD33NDVR2Y4DI2NZP7RTL7BT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT/action/storage_attestation","attest_author":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT/action/author_attestation","sign_citation":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT/action/citation_signature","submit_replication":"https://pith.science/pith/BXRD33NDVR2Y4DI2NZP7RTL7BT/action/replication_record"}},"created_at":"2026-07-05T11:09:15.416829+00:00","updated_at":"2026-07-05T11:09:15.416829+00:00"}