Related papers: Just Do It!? Computer-Use Agents Exhibit Blind Goa…
The major function of this model is to access the UCI Wisconsin Breast Can- cer data-set[1] and classify the data items into two categories, which are normal and anomalous. This kind of classifi cation can be referred as anomaly detection,…
Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to the best explanation'…
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on…
Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either detect deception without task integration or document attacks…
Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of…
Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn…
Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We…
As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are embedded into the…
Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LLMs have received significant attention, no benchmark exists…
Advancements in AI have led to agents in networked environments increasingly mirroring human behavior, thereby blurring the boundary between artificial and human actors in specific contexts. This shift brings about significant challenges in…
Agentic AI increasingly intervenes proactively by inferring users' situations from contextual data yet often fails for lack of principled judgment about when, why, and whether to act. We address this gap by proposing a conceptual model that…
Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…
The "gender" of intelligent agents, virtual characters, social robots, and other agentic machines has emerged as a fundamental topic in studies of people's interactions with computers. Perceptions of agent gender can help explain user…
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, including task rewards and intrinsic motivation. However, it is…
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic…
Despite advances in assistive technologies, Blind and Low-Vision (BLV) individuals continue to face challenges in understanding their surroundings. Delivering concise, useful, and timely scene descriptions for ambient perception remains a…
Affect Control Theory (ACT) is a powerful and general sociological model of human affective interaction. ACT provides an empirically derived mathematical model of culturally shared sentiments as heuristic guides for human decision making.…
Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially cause catastrophic…