{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2N3GJTI6LAQ4MQICLWOGUOEE5J","short_pith_number":"pith:2N3GJTI6","schema_version":"1.0","canonical_sha256":"d37664cd1e5821c641025d9c6a3884ea42ee0e5134d3ab8da5742898319726ad","source":{"kind":"arxiv","id":"2510.18383","version":3},"attestation_state":"computed","paper":{"title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changsu Choi, Dongyeon Kim, Hoyun Song, KyungTae Lim, MinKyung Cho, NohHyeob Bae, Seona Yu, Sunjin Park, WooHyeon Jung","submitted_at":"2025-10-21T08:03:14Z","abstract_excerpt":"Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we "},"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":"2510.18383","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T08:03:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eff2a52967e69fbdd5718bd88c715f51afdd918b4616b73e57e01d056750717b","abstract_canon_sha256":"18f7ffcf58720d3499b852a2ae3a5bea4751c042e0094252898047a5c9945462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:15.767203Z","signature_b64":"vOmZlxxOSA6WrWMQJQ+xhMYbD90W0HgHr8TYajDY4sfrnU7CFilsb0cFVcVRSxORPcECuzBBCZh8kNWTr0nHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d37664cd1e5821c641025d9c6a3884ea42ee0e5134d3ab8da5742898319726ad","last_reissued_at":"2026-06-19T16:12:15.766756Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:15.766756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changsu Choi, Dongyeon Kim, Hoyun Song, KyungTae Lim, MinKyung Cho, NohHyeob Bae, Seona Yu, Sunjin Park, WooHyeon Jung","submitted_at":"2025-10-21T08:03:14Z","abstract_excerpt":"Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18383","kind":"arxiv","version":3},"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/2510.18383/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":"2510.18383","created_at":"2026-06-19T16:12:15.766813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.18383v3","created_at":"2026-06-19T16:12:15.766813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18383","created_at":"2026-06-19T16:12:15.766813+00:00"},{"alias_kind":"pith_short_12","alias_value":"2N3GJTI6LAQ4","created_at":"2026-06-19T16:12:15.766813+00:00"},{"alias_kind":"pith_short_16","alias_value":"2N3GJTI6LAQ4MQIC","created_at":"2026-06-19T16:12:15.766813+00:00"},{"alias_kind":"pith_short_8","alias_value":"2N3GJTI6","created_at":"2026-06-19T16:12:15.766813+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/2N3GJTI6LAQ4MQICLWOGUOEE5J","json":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J.json","graph_json":"https://pith.science/api/pith-number/2N3GJTI6LAQ4MQICLWOGUOEE5J/graph.json","events_json":"https://pith.science/api/pith-number/2N3GJTI6LAQ4MQICLWOGUOEE5J/events.json","paper":"https://pith.science/paper/2N3GJTI6"},"agent_actions":{"view_html":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J","download_json":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J.json","view_paper":"https://pith.science/paper/2N3GJTI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.18383&json=true","fetch_graph":"https://pith.science/api/pith-number/2N3GJTI6LAQ4MQICLWOGUOEE5J/graph.json","fetch_events":"https://pith.science/api/pith-number/2N3GJTI6LAQ4MQICLWOGUOEE5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J/action/storage_attestation","attest_author":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J/action/author_attestation","sign_citation":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J/action/citation_signature","submit_replication":"https://pith.science/pith/2N3GJTI6LAQ4MQICLWOGUOEE5J/action/replication_record"}},"created_at":"2026-06-19T16:12:15.766813+00:00","updated_at":"2026-06-19T16:12:15.766813+00:00"}