CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
Graphical user interface (GUI) agents powered by vision language models (VLMs) are rapidly moving from passive assistance to autonomous operation. However, this unrestricted action space exposes users to severe and irreversible financial, privacy or social harm. Existing safeguards rely on prompt engineering, brittle heuristics and VLM-as-critic lack formal verification and user-tunable guarantees. We propose CORA (COnformal Risk-controlled GUI Agent), a post-policy, pre-action safeguarding framework that provides statistical guarantees on harmful executed actions. CORA reformulates safety as selective action execution: we train a Guardian model to estimate action-conditional risk for each proposed step. Rather than thresholding raw scores, we leverage Conformal Risk Control to calibrate an execute/abstain boundary that satisfies a user-specified risk budget and route rejected actions to a trainable Diagnostician model, which performs multimodal reasoning over rejected actions to recommend interventions (e.g., confirm, reflect, or abort) to minimize user burden. A Goal-Lock mechanism anchors assessment to a clarified, frozen user intent to resist visual injection attacks. To rigorously evaluate this paradigm, we introduce Phone-Harm, a new benchmark of mobile safety violations with step-level harm labels under real-world settings. Experiments on Phone-Harm and public benchmarks against diverse baselines validate that CORA improves the safety--helpfulness--interruption Pareto frontier, offering a practical, statistically grounded safety paradigm for autonomous GUI execution. Code and benchmark are available at cora-agent.github.io.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningPrompt EngineeringSimilar Papers 제목 키워드 기반
SPARC: Prediction-Based Safe Control for Coupled Controllable and Uncontrollable Agents with Conformal Predictions
We investigate the problem of safe control synthesis for systems operating in environments with uncontrollable agents whose dynamics are unknown but coupled with those of the controlled system. This scenario naturally ar…
Autonomous DrivingConformal PredictionPredictionDistribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation
We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for forecasted quality scores. Conformal intervals achieve cal…
Conformalized Rate-Adaptive Sensing
Many high-resolution imaging systems face the same fundamental question: when have enough measurements been collected to reconstruct an image accurately? We develop Conformalized Rate-Adaptive Sensing (CoRAS), a method t…
Image ReconstructionConformal Loss-Controlling Prediction
Conformal prediction is a learning framework controlling prediction coverage of prediction sets, which can be built on any learning algorithm for point prediction. This work proposes a learning framework named conformal …
Conformal PredictionPredictionWeather ForecastingMulti-Agent Reachability Calibration with Conformal Prediction
We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning. Given a learning-based forecasting model …
Autonomous DrivingConformal PredictionPredictionquantile regression+2