arXiv AI
Jul 1
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
arXiv:2606. 30697v1 Announce Type: cross Abstract: Current operating systems expose interfaces optimized for human users but not for AI agents.
Tactile: Giving Computer-Using Agents Hands and Feet
arXiv:2607. 14443v1 Announce Type: new Abstract: Computer-use agents are becoming capable software operators, but their interface to desktop applications is still often a brittle motor layer: they look at screenshots, predict coordinates, click, and hope that the visible state changed as intended.
Related stories
arXiv AI
Aug 28
ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions
The paper introduces ASIL, an Agent‑Software Interaction Layer that replaces traditional screenshot‑and‑click interfaces with structured JSON observations and code‑executable semantic actions. ASIL is implemented across 15 applications and evaluated on 300 single‑application and 80 multi‑application tasks, achieving over 80% success with fewer than five actions per task. The structured interface also improves training efficiency, boosting performance of Qwen models from 58–66% to 72–80% with small‑scale supervised fine‑tuning and further gains with on‑policy reinforcement learning.
arXiv Computation and Language
Sep 21
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Re...
arXiv AI
Aug 12
Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents
arXiv:2608. 09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure behind visual layout.
arXiv AI
Jun 9
Syll: Open-Source Personal Automation with Cross-Surface Execution
arXiv:2606. 07594v1 Announce Type: new Abstract: Personal AI agents must increasingly operate across APIs, shells, web surfaces, and desktop GUIs, yet many systems remain tuned to a single interface and offer limited support for user teaching and auditability.
arXiv AI
Jun 16
OSGuard: A Benchmark for Safety in Computer-Use Agents
arXiv:2606. 15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks.
arXiv AI
Jun 11
Grounding Computer Use Agents on Human Demonstrations
arXiv:2511. 07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements.
arXiv Machine Learning
Sep 22
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
arXiv:2609.24890v1 Announce Type: cross Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with f...
arXiv AI
Jun 30
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
arXiv:2606. 29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.
arXiv AI
Jul 15
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
arXiv:2606. 29537v2 Announce Type: replace Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.
arXiv AI
Jun 3
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration
arXiv:2606. 03103v1 Announce Type: new Abstract: Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses.
arXiv AI
Jun 24
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents
arXiv:2606. 24551v1 Announce Type: new Abstract: Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with differences in tasks, initial states, verifiers, and permitted actions.