Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL

[2608.14945] Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14945 (cs) [Submitted on 14 Aug 2026] Title: Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL Authors: Qizhen Lan , Xi Xiao , Xiangchen Guan , Mengchen Fan , Moule Lin , Jung Im Choi , Lijing Zhu View a PDF of the paper titled Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL, by Qizhen Lan and 6 other authors View PDF HTML (experimental) Abstract: On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories. Existing methods allocate this supervision mainly by teacher trust, but trust does not reveal whether emphasizing a token supports the current policy objective. We call this the trust-utility mismatch and introduce Influence Calibration for Self-Distillation (ICSD). For each supervised token, ICSD measures the first-order response of its importance-weighted RL surrogate contribution to a teacher-directed output perturbation. Batch-adaptive calibration converts this non-stationary signal into a bounded allocation weight while preserving the original auxiliary-loss mass within each action turn. These detached weights affect only the distillation loss and require no additional model pass. Across ALFWorld, WebShop, and Search-QA, ICSD improves all matched aggregate metrics over trust-only allocation under Group Relative Policy Optimization (GRPO) and Group-in-Group Policy Optimization (GiGPO), across two model families spanning 1.5B to 7B. At 7B, it reaches 96.1% ALFWorld success and a WebShop score of 93.1. Frozen-batch analyses show that ICSD reduces teacher-supported mass assigned to objective-opposed tokens from 60.1% to 37.8% and raises cosine compatibility with the RL gradient by 0.192. A companion repository is avail- able at this https URL . Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL) Cite as: arXiv:2608.14945 [cs.AI] (or arXiv:2608.14945v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14945 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Qizhen Lan [ view email ] [v1] Fri, 14 Aug 2026 23:56:38 UTC (6,357 KB) Full-text links: Access Paper: View a PDF of the paper titled Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL, by Qizhen Lan and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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) Major funding support from

Related documents

• No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation#1129003
• Interactive-Policy Distillation with Bidirectional Propose-and-Verify#1131747
• Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement#819076
• Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement#809084
• From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation#1161023