OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
Autodroid: Llm-powered task automation in android, 2024
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
Introduces an app-content instrumentation framework and benchmark showing that examined GUI agents suffer 42.0% and 36.1% average misleading rates from third-party content in dynamic and static tests respectively.
InfiGUI-R1 uses Reasoning Injection via spatial distillation followed by Deliberation Enhancement via RL to evolve GUI agents from reactive actors to deliberative reasoners, reporting strong performance on grounding and trajectory tasks.
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
ClawMobile proposes a hierarchical system separating probabilistic LLM planning from structured deterministic execution to improve stability and reproducibility of agentic systems on real smartphones.
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
citing papers explorer
-
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps