Related papers: SPILLage: Agentic Oversharing on the Web
Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work suggests that many of these failures stem from weaknesses in planning, yet…
LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance…
Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate…
Imagine AI assistants that enhance conversations without interrupting them: quietly providing relevant information during a medical consultation, seamlessly preparing materials as teachers discuss lesson plans, or unobtrusively scheduling…
Online social networks have dramatically altered the landscape of public discourse, creating both opportunities for enhanced civic participation and risks of deepening social divisions. Prevalent approaches to studying online polarization…
For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat…
With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…
The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…
This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are software that automate Web browsing using large language models and ancillary tooling. However,…
Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation…
Consider a multi-agent systems setup in which a principal (a supervisor agent) assigns subtasks to specialized agents and aggregates their responses into a single system-level output. A core property of such systems is information…
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks…
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…
Large Language Models (LLMs) have shown capabilities close to human performance in various analytical tasks, leading researchers to use them for time and labor-intensive analyses. However, their capability to handle highly specialized and…
Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively…
When interacting with people, AI agents do not just influence the state of the world -- they also influence the actions people take in response to the agent, and even their underlying intentions and strategies. Accounting for and leveraging…
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…
Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact with the internet at the user's behest, such as navigating…
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…
A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This renders environmental state and progress towards completing a…