
research note
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
OpenComputer addresses the challenge of constructing realistic, verifiable software environments for computer-use agents that operate real desktop applications

research note
OpenComputer addresses the challenge of constructing realistic, verifiable software environments for computer-use agents that operate real desktop applications

research note
The paper addresses the challenge of costly and slow A/B testing in e-commerce, where diverting real traffic to experimental variants can degrade user experience and require weeks for statistical s…

research note
This paper addresses the fundamental question in accessibility computing of how far AI-driven accessibility systems can extend their operational capabilities

research note
WEASEL addresses two critical challenges in training large language model (LLM)-based web agents — out-of-domain generalization and training inefficiency caused by noisy, redundant offline web inter…

research note
The paper addresses a critical limitation in current GUI agents: their dependence on static parametric knowledge from pre-training or instruction tuning, which hampers their ability to solve long-t…

research note
This paper addresses a critical and under-explored failure mode in multimodal agents that control tool calls—hallucination-to-action conversion (H2AC)

research note
This paper addresses the unresolved question of how electronic dimensionality influences magnetism and superconductivity in Ruddlesden-Popper nickelates, a family of layered correlated materials st…

research note
This paper introduces MEEDAV, an open-source, web-based tool designed to synchronously visualize and explore multimodal psycholinguistic data streams—specifically EEG, eye-tracking, and audio recor…

research note
This paper addresses an abstract obstruction theorem concerning primitive closure predicates defined on a minimal propositional language of falsity and implication within a constructive metatheory

research note
This paper addresses the challenge of automatically subclassifying invalid bug reports by their root causes and generating corresponding no-code fixes—resolutions that do not require source code ch…

research note
This paper presents a controlled, reproducible benchmark experiment evaluating state-of-the-art language models on the task of rediscovering six publicly disclosed Mythos-linked system-level securi…

research note
This paper addresses the challenge of interactive large graph visualization directly in web browsers, without requiring dedicated servers