Structured tool calls often fail after only a small number of fields violate a schema or an execution contract. Regenerating the complete object enlarges the action surface and makes repeated repair difficult to audit. We introduce ContractRL, a contract-constrained sequential repair protocol that models verifier-guide...
Miao-Bo Hu, Shu-Hao Hu, Xiao-Bo Guo et al.· 0 citations
Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal information of an unqueried verifier on a sealed calibration split, discounts uncertaint...
Miao-Bo Hu, Shu-Hao Hu, Xiao-Bo Guo et al.· 0 citations
Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide heterogeneous degradation and become fragile when the deployment mixture of information states changes. We introduce RSD-Poker, a structure-adaptive and shift-robust cert...
Miao-Bo Hu, Shu-Hao Hu, Xiao-Bo Guo et al.· 0 citations
Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates discrete directional admission from continuous magnitude control. An observation-only accept-appeal-abstain policy uses a finite secondary-verification budg...
Miao-Bo Hu, Shu-Hao Hu, Xiao-Bo Guo et al.· 0 citations
Observation-safe counterfactual coupling (OSCC) is introduced, a framework that defines an admissible class through marginal preservation, information-state safety, branch-local policy randomness, semantic event alignment, and trace-before-oracle replay.
Miao-Bo Hu, Shu-Hao Hu, Xiao-Bo Guo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.