{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCRY7AAYPDF2IIAX6UYZRIQ552","short_pith_number":"pith:OCRY7AAY","schema_version":"1.0","canonical_sha256":"70a38f801878cba42017f53198a21deebe459497f64a99d28aa98a91871f5901","source":{"kind":"arxiv","id":"2506.00439","version":1},"attestation_state":"computed","paper":{"title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Guojun Yin, Jiajun Chai, Qichao Zhang, Wei Lin, Yuanheng Zhu, Yuqian Fu","submitted_at":"2025-05-31T07:38:41Z","abstract_excerpt":"Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting strategies that fail to adapt to the dynamic, context-dependent characteristics of LLM capabilities. In this work, we propose Reinforcement Learning-Assisted Ensemble for LLMs (RLAE), a novel framework that reformulates LLM ensemble through the lens of a Markov Decision Process (MDP). Our approach introduces a RL agent that dynamically adjusts ensemble weights"},"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":"2506.00439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T07:38:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6befd0b8159f7e7ffecc099d1a6eb9bdc74076c769f6a22a75c2b12ae741e56f","abstract_canon_sha256":"0300172433a1e2d9db6455cf275893c506a4737b5634821fca37459052568392"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:34.773890Z","signature_b64":"K74uZddEZNEQ3YSgn02XXzT/ZgrvVe7FysRf9qDtmlbX1HDwdHejAVnULsIFnZJBtPSXkqd9EjnDAGe7GqNJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a38f801878cba42017f53198a21deebe459497f64a99d28aa98a91871f5901","last_reissued_at":"2026-07-05T11:13:34.773363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:34.773363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Guojun Yin, Jiajun Chai, Qichao Zhang, Wei Lin, Yuanheng Zhu, Yuqian Fu","submitted_at":"2025-05-31T07:38:41Z","abstract_excerpt":"Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting strategies that fail to adapt to the dynamic, context-dependent characteristics of LLM capabilities. In this work, we propose Reinforcement Learning-Assisted Ensemble for LLMs (RLAE), a novel framework that reformulates LLM ensemble through the lens of a Markov Decision Process (MDP). Our approach introduces a RL agent that dynamically adjusts ensemble weights"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00439","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/2506.00439/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":"2506.00439","created_at":"2026-07-05T11:13:34.773422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00439v1","created_at":"2026-07-05T11:13:34.773422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00439","created_at":"2026-07-05T11:13:34.773422+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCRY7AAYPDF2","created_at":"2026-07-05T11:13:34.773422+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCRY7AAYPDF2IIAX","created_at":"2026-07-05T11:13:34.773422+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCRY7AAY","created_at":"2026-07-05T11:13:34.773422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.10971","citing_title":"RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552","json":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552.json","graph_json":"https://pith.science/api/pith-number/OCRY7AAYPDF2IIAX6UYZRIQ552/graph.json","events_json":"https://pith.science/api/pith-number/OCRY7AAYPDF2IIAX6UYZRIQ552/events.json","paper":"https://pith.science/paper/OCRY7AAY"},"agent_actions":{"view_html":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552","download_json":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552.json","view_paper":"https://pith.science/paper/OCRY7AAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00439&json=true","fetch_graph":"https://pith.science/api/pith-number/OCRY7AAYPDF2IIAX6UYZRIQ552/graph.json","fetch_events":"https://pith.science/api/pith-number/OCRY7AAYPDF2IIAX6UYZRIQ552/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552/action/storage_attestation","attest_author":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552/action/author_attestation","sign_citation":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552/action/citation_signature","submit_replication":"https://pith.science/pith/OCRY7AAYPDF2IIAX6UYZRIQ552/action/replication_record"}},"created_at":"2026-07-05T11:13:34.773422+00:00","updated_at":"2026-07-05T11:13:34.773422+00:00"}