Related papers: RISK: A Framework for GUI Agents in E-commerce Ris…
We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine…
Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 enables intervention; one that reports it at step 48 provides only forensic value.…
The manifold interactions between safety and security aspects makes it plausible to handle safety and security risks in an unified way. The paper develops a corresponding approach based on the discrete event systems (DEVS) paradigm. The…
Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or…
Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…
The rapid advancement of information technology has introduced a noticeable shift from traditional offline practices to more efficient and interconnected online environments. This transition, while offering convenience, has also increased…
Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…
Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and…
High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large language model (LLM) assistants can generate text, but they do not…
Software defects rediscovered by a large number of customers affect various stakeholders and may: 1) hint at gaps in a software manufacturer's Quality Assurance (QA) processes, 2) lead to an over-load of a software manufacturer's support…
Autonomous vehicles hold great promise for reducing traffic fatalities and improving transportation efficiency, yet their widespread adoption hinges on embedding credible and transparent ethical reasoning into routine and emergency…
The European Union (EU) has long favored a risk-based approach to regulation. Such an approach is also used in recent cyber security legislation enacted in the EU. Risks are also inherently related to compliance with the new legislation.…
This paper presents the first multistakeholder approach for translating diverse stakeholder values into an evaluation metric setup for Recommender Systems (RecSys) in digital archives. While commercial platforms mainly rely on engagement…
Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real…
In multi-agent safety-critical scenarios, traditional autonomous driving frameworks face significant challenges in balancing safety constraints and task performance. These frameworks struggle to quantify dynamic interaction risks in…
When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to recognize when it is likely to fail in a novel situation and to…
Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end…
Performance regression testing is essential in large-scale continuous-integration (CI) systems, yet executing full performance suites for every commit is prohibitively expensive. Prior work on performance regression prediction and batch…
AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…
We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning.…