Related papers: The Tool Illusion: Rethinking Tool Use in Web Agen…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
With advances in generative AI, there is increasing work towards creating autonomous agents that can manage daily tasks by operating user interfaces (UIs). While prior research has studied the mechanics of how AI agents might navigate UIs…
This paper presents our research towards a near-term future in which legal entities, such as individuals and organisations can entrust semi-autonomous AI-driven agents to carry out online interactions on their behalf. The author's research…
Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as document analysis, question answering (Q&A), and literature search. However, system…
As the power of Artificial Intelligence (AI) continues to advance, there is increased interest in how best to combine AI-based agents with humans to achieve mission effectiveness. Three perspectives have emerged. The first stems from more…
Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user…
Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
The inevitable incompleteness of any collection of PMESII models, along with poorly understood methods for combining heterogeneous models, leads to major uncertainty regarding the reliability of computational tools. This uncertainty is…
Working with data in table form is usually considered a preparatory and tedious step in the sensemaking pipeline; a way of getting the data ready for more sophisticated visualization and analytical tools. But for many people, spreadsheets…
This paper presents our methodology to simulate the behavior of the DeLend Platform. Such simulations are important to verify if the system is able to connect the different sets of agents linked to the platform in a functional manner. They…
Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled…
We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking…
This paper introduces two ongoing research projects which seek to apply computer modelling techniques in order to simulate human behaviour within organisations. Previous research in other disciplines has suggested that complex social…
The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines, including computer science and social science. Recent advancements in Artificial Intelligence (AI) have significantly reshaped…
Artificial Intelligence (AI) is advancing at an unprecedented pace, with clear potential to enhance decision-making and productivity. Yet, the collaborative decision-making process between humans and AI remains underdeveloped, often falling…
Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlooked limitation of these agents is that they, by default, assume a stationary context, failing…
The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows. However, current tool-use benchmarks remain misaligned with real-world requirements,…
Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…
We introduce Reagent, a technology that readily converts ordinary webpages containing structured data into software agents with which one can interact naturally, via a combination of speech and pointing. Previous efforts to make webpage…