arXiv:2606. 13239v1 Announce Type: cross Abstract: Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces.
arXiv:2606. 09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools.
ComponentBench is a new benchmark that evaluates computer‑use agents at the component level on modern web UIs. It contains 97 canonical UI components and 2,910 programmatically verified tasks, along with cleaned human reference trajectories for measuring task success and interaction efficiency. The benchmark also offers a scalable pipeline for auditing structural difficulty and synthesizing failure analyses across tasks and component families.
arXiv:2607. 22689v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs).
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.
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termi...
arXiv:2607. 11818v1 Announce Type: cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents.
arXiv:2608. 15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution.
Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, s...
arXiv:2609.16251v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engi...
ToolCUA is an end‑to‑end agent that learns to optimally orchestrate GUI actions and tool calls for Computer Use Agents. It introduces a staged training pipeline that first scales interleaved GUI‑tool trajectories from static GUI data, then bootstraps decision making with single‑turn reinforcement learning, and finally refines performance via online agentic RL guided by a tool‑efficient path reward. On the OSWorld‑MCP benchmark, ToolCUA achieves 46.85% accuracy, a 66% relative improvement over the baseline and a 3.9% gain over GUI‑only models, setting a new state of the art for comparable‑scale models.
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.
AnyAct introduces a universal action layer that consolidates diverse tool capabilities into a self‑evolving action space for AI agents operating in open‑world environments. It tackles the scale dilemma, tool non‑stationarity, and heterogeneous feedback by using hierarchical progressive retrieval and test‑time reliability evolution, while a heterogeneous observation grounding module unifies multi‑modal feedback. Evaluations on LiveMCPBench and the newly created OSMCP benchmark show state‑of‑the‑art performance, with significant gains in task success rate and reduced execution steps, especially for models with limited native capabilities.