{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DXHY7QOIR3HSDCZ5UKT5WH22GR","short_pith_number":"pith:DXHY7QOI","schema_version":"1.0","canonical_sha256":"1dcf8fc1c88ecf218b3da2a7db1f5a346c995a28f03c97be6fb2621cac927be5","source":{"kind":"arxiv","id":"2506.00396","version":1},"attestation_state":"computed","paper":{"title":"Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Gu, Shangsong Liang","submitted_at":"2025-05-31T05:32:12Z","abstract_excerpt":"Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealing that existing methods often trade significant efficiency for marginal performance gains. To improve LLM decision-making while maintaining efficiency, we propose the Speculative Reward Model (SRM), a plug-and-play framework that seamlessly"},"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":"2506.00396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T05:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"84e4826fe2f5828d4ba30f3588f5871accab439491fe9f5ab126c0971e241719","abstract_canon_sha256":"1c283b308cfdaaad00b97c1c742d28c3b6224f82465dd47a1a91089c8265ad8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:33.951973Z","signature_b64":"pymUoyrJ+EpJ14a23uzoFeGTkqHrdIHJ1J2vtt/U3zCRb+XY8Of5sbCMVhoQhKg656v0cDXGisRmVqfjNmTBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dcf8fc1c88ecf218b3da2a7db1f5a346c995a28f03c97be6fb2621cac927be5","last_reissued_at":"2026-07-05T11:13:33.951578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:33.951578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Gu, Shangsong Liang","submitted_at":"2025-05-31T05:32:12Z","abstract_excerpt":"Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealing that existing methods often trade significant efficiency for marginal performance gains. To improve LLM decision-making while maintaining efficiency, we propose the Speculative Reward Model (SRM), a plug-and-play framework that seamlessly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00396","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/2506.00396/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":"2506.00396","created_at":"2026-07-05T11:13:33.951639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00396v1","created_at":"2026-07-05T11:13:33.951639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00396","created_at":"2026-07-05T11:13:33.951639+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXHY7QOIR3HS","created_at":"2026-07-05T11:13:33.951639+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXHY7QOIR3HSDCZ5","created_at":"2026-07-05T11:13:33.951639+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXHY7QOI","created_at":"2026-07-05T11:13:33.951639+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/DXHY7QOIR3HSDCZ5UKT5WH22GR","json":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR.json","graph_json":"https://pith.science/api/pith-number/DXHY7QOIR3HSDCZ5UKT5WH22GR/graph.json","events_json":"https://pith.science/api/pith-number/DXHY7QOIR3HSDCZ5UKT5WH22GR/events.json","paper":"https://pith.science/paper/DXHY7QOI"},"agent_actions":{"view_html":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR","download_json":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR.json","view_paper":"https://pith.science/paper/DXHY7QOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00396&json=true","fetch_graph":"https://pith.science/api/pith-number/DXHY7QOIR3HSDCZ5UKT5WH22GR/graph.json","fetch_events":"https://pith.science/api/pith-number/DXHY7QOIR3HSDCZ5UKT5WH22GR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR/action/storage_attestation","attest_author":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR/action/author_attestation","sign_citation":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR/action/citation_signature","submit_replication":"https://pith.science/pith/DXHY7QOIR3HSDCZ5UKT5WH22GR/action/replication_record"}},"created_at":"2026-07-05T11:13:33.951639+00:00","updated_at":"2026-07-05T11:13:33.951639+00:00"}