{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2RYTZS34WMZMQI5RTH7DGMX5UU","short_pith_number":"pith:2RYTZS34","schema_version":"1.0","canonical_sha256":"d4713ccb7cb332c823b199fe3332fda529f5dae2b9ae4a1527deb400f9dd1402","source":{"kind":"arxiv","id":"2604.03675","version":3},"attestation_state":"computed","paper":{"title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OASES improves agentic search by co-training policies with outcome-aligned evaluators for better process rewards.","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Erhan Zhang, Jiaxin Mao, Wei Yang, Xiaochi Wei, Yan Gao, Yao Hu, Yiqun Chen, Yi Wu, Zechun Niu","submitted_at":"2026-04-04T10:23:46Z","abstract_excerpt":"Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm for search agents, yet outcome-only rewards are sparse and provide limited credit assignment for intermediate search actions. Existing process-reward methods therefore seek to densify supervision through proxy signals, external evaluators, or likelihood-based information gain. However, proxy rewards can deviate from the final outcome objective, while fixed "},"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":true},"canonical_record":{"source":{"id":"2604.03675","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-04T10:23:46Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"bcac663e8edd466d1911229db2b77e3a43cbca804b9ff5130cce9540ded13485","abstract_canon_sha256":"2a8d2fcba6312f453f9406c66e80f6951f3c8790171ffa936b2134e3ff1ae125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:29.357482Z","signature_b64":"w1y25hn3uspC8pjlp8Xf2FRQx+d/MV5U+XfCfB5+m0VpoChlPoBRw7cxuIuFMZwNjA8O9v+CpYx92gVLJzKzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4713ccb7cb332c823b199fe3332fda529f5dae2b9ae4a1527deb400f9dd1402","last_reissued_at":"2026-05-26T01:03:29.356430Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:29.356430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OASES improves agentic search by co-training policies with outcome-aligned evaluators for better process rewards.","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Erhan Zhang, Jiaxin Mao, Wei Yang, Xiaochi Wei, Yan Gao, Yao Hu, Yiqun Chen, Yi Wu, Zechun Niu","submitted_at":"2026-04-04T10:23:46Z","abstract_excerpt":"Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm for search agents, yet outcome-only rewards are sparse and provide limited credit assignment for intermediate search actions. Existing process-reward methods therefore seek to densify supervision through proxy signals, external evaluators, or likelihood-based information gain. However, proxy rewards can deviate from the final outcome objective, while fixed "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That co-training the evaluator on the evolving policy will produce reliable, non-stale process rewards without introducing new biases or instability that undermine the final outcome alignment.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OASES co-trains search policies and evaluators to generate outcome-aligned process rewards, outperforming standard RL baselines on five multi-hop QA benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OASES improves agentic search by co-training policies with outcome-aligned evaluators for better process rewards.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"55f67e31d805cec2b98399c31057da4981cf0b50f6bb63a6d9bd6005e6302495"},"source":{"id":"2604.03675","kind":"arxiv","version":3},"verdict":{"id":"b6697de3-c9bc-4f17-89f1-3de54d8a77fb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T17:12:43.396904Z","strongest_claim":"Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.","one_line_summary":"OASES co-trains search policies and evaluators to generate outcome-aligned process rewards, outperforming standard RL baselines on five multi-hop QA benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That co-training the evaluator on the evolving policy will produce reliable, non-stale process rewards without introducing new biases or instability that undermine the final outcome alignment.","pith_extraction_headline":"OASES improves agentic search by co-training policies with outcome-aligned evaluators for better process rewards."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03675/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":1,"snapshot_sha256":"08e6c632355f317b811f748568968728fb6ae2cef81d28a9178b43a5bb8f8421"},"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":"2604.03675","created_at":"2026-05-26T01:03:29.356574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.03675v3","created_at":"2026-05-26T01:03:29.356574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03675","created_at":"2026-05-26T01:03:29.356574+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RYTZS34WMZM","created_at":"2026-05-26T01:03:29.356574+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RYTZS34WMZMQI5R","created_at":"2026-05-26T01:03:29.356574+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RYTZS34","created_at":"2026-05-26T01:03:29.356574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU","json":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU.json","graph_json":"https://pith.science/api/pith-number/2RYTZS34WMZMQI5RTH7DGMX5UU/graph.json","events_json":"https://pith.science/api/pith-number/2RYTZS34WMZMQI5RTH7DGMX5UU/events.json","paper":"https://pith.science/paper/2RYTZS34"},"agent_actions":{"view_html":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU","download_json":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU.json","view_paper":"https://pith.science/paper/2RYTZS34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.03675&json=true","fetch_graph":"https://pith.science/api/pith-number/2RYTZS34WMZMQI5RTH7DGMX5UU/graph.json","fetch_events":"https://pith.science/api/pith-number/2RYTZS34WMZMQI5RTH7DGMX5UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU/action/storage_attestation","attest_author":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU/action/author_attestation","sign_citation":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU/action/citation_signature","submit_replication":"https://pith.science/pith/2RYTZS34WMZMQI5RTH7DGMX5UU/action/replication_record"}},"created_at":"2026-05-26T01:03:29.356574+00:00","updated_at":"2026-05-26T01:03:29.356574+00:00"}