MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation

[2510.18383] MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2510.18383 (cs) [Submitted on 21 Oct 2025 ( v1 ), last revised 27 Aug 2026 (this version, v4)] Title: MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation Authors: ChangSu Choi , Hoyun Song , Dongyeon Kim , Minkyung Cho , WooHyeon Jung , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim View PDF HTML (experimental) Abstract: 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), is an off-policy distillation method that suffers from poor out-of-domain (OOD) generalization because it rigidly aligns 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 propose MENTOR, an on-policy distillation framework that introduces a flexible yet process-aware reward structure. Instead of enforcing rigid replication, MENTOR uses the teacher's reference to guide tool-use behavior, balancing behavioral alignment with downstream performance. Extensive experiments on controlled executable-tool benchmarks demonstrate that MENTOR improves OOD tool-use performance compared to SFT and strict RL baselines. Our findings suggest that within verifiable tool-use environments, flexible tool-use alignment offers a more effective approach than strict trajectory replication for developing adaptable small models. Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2510.18383 [cs.CL] (or arXiv:2510.18383v4 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2510.18383 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hoyun Song [ view email ] [v1] Tue, 21 Oct 2025 08:03:14 UTC (7,516 KB) [v2] Tue, 28 Oct 2025 04:50:06 UTC (7,516 KB) [v3] Thu, 18 Jun 2026 07:59:59 UTC (315 KB) [v4] Thu, 27 Aug 2026 11:10:56 UTC (316 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2025-10 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation#677439
• Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning#618605
• Evolving Support Priorities in Empathetic Reinforcement Learning#1119322
• OPSRD: On-Policy Self-Role Distillation#1145051
• PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning#617852