Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls

Abstract:Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body but should not determine a recipient, account, command, or credential. Existing statistical methods typically control risk over the entire action, allowing failures in rare, high-risk fields to be obscured by benign arguments. We introduce role-stratified per-field conformal risk control, a calibration layer that wraps any per-field detector and sets separate thresholds and risk budgets for semantic argument roles. For a role with prevalence $p_r$, aggregate-only certification must use an effective budget of $\alpha p_r$ to guarantee role-specific risk $\alpha$, whereas role-stratified calibration certifies each sufficiently sampled role directly with a finite-sample guarantee; rarer roles are handled by pooled certification. Across AgentDojo and InjecAgent with six language models, the empirical utility gap tracks this predicted price of coarseness, and our method achieves the most consistent role-specific budget compliance under model and attack transfer, detector noise, gradual drift, unseen tool suites, and adaptive attacks. It provides formal per-role guarantees under exchangeability or after recalibration, and empirical compliance under frozen distribution shift. These results suggest that structured tool calls should be certified at the semantic-role level, not the whole action.

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

arXiv:2607.24343 [cs.LG]

(or arXiv:2607.24343v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.24343 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

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.