Related papers: On the Reliability of Computer Use Agents
Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume that observed behavior…
Agents for computer use (ACUs) are an emerging class of systems capable of executing complex tasks on digital devices -- such as desktops, mobile phones, and web platforms -- given instructions in natural language. These agents can automate…
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…
We consider the setting of stochastic multiagent systems modelled as stochastic multiplayer games and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a…
Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical…
As coding agents have seen rapid capability and adoption gains, users are applying them to general tasks beyond software engineering. In this post, we investigate whether coding agents can successfully generalize to end-to-end business…
We investigate the problem of autonomous agents processing pieces of information that may be corrupted (tainted). Agents have the option of contacting a central database for a reliable check of the status of the message, but this procedure…
Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically address. We show that a 1MB replay script that blindly executes a recorded action sequence…
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…
In many real-world continuous action domains, human agents must decide which actions to attempt and then execute those actions to the best of their ability. However, humans cannot execute actions without error. Human performance in these…
As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…
Current discourse on Artificial Intelligence (AI) ethics, dominated by "trustworthy" and "responsible" AI, overlooks a more fundamental human-computer interaction (HCI) crisis: the erosion of human agency. This paper argues that the primary…
Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…
Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…
When interacting with other decision-making agents in non-adversarial scenarios, it is critical for an autonomous agent to have inferable behavior: The agent's actions must convey their intention and strategy. We model the inferability…
LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent accuracy across domains, they mostly…
Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem…
Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline,…
Quantum computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification. However, less is known about the advantages that quantum computers may bring in the setting of…
Game-theoretic dynamics between AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is…