Holo4: powering generalist computer-use agents

Holo3.1: Fast & Local Computer Use Agents

Computer-Using Agent

Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

Tiny Agents: an MCP-powered agent in 50 lines of code

Smol2Operator: Post-Training GUI Agents for Computer Use

Terminal Agents Suffice for Enterprise Automation

arXiv:2604. 00073v3 Announce Type: replace-cross Abstract: There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously.

ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis

arXiv:2605. 25160v2 Announce Type: replace Abstract: GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments.

Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers

arXiv:2607. 14158v1 Announce Type: new Abstract: This position paper explores how Agentic AI and Model Context Protocol (MCP) can support power-grid studies in a Transmission System Operator (TSO) context.

Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications

The study evaluates computer-use agents (CUAs) for blind users by conducting a three‑week diary study with eight participants using the OLLA prototype. Across 1,258 commands in 12 desktop applications, GPT‑5 achieved the highest success rate of 52.5%, while analysis uncovered failures in grounding, planning, constraint‑tracking, and termination. Interviews highlighted additional needs beyond automation for blind users.

Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents

arXiv:2608. 13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols.

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

arXiv:2607. 14611v1 Announce Type: cross Abstract: A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases.