Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: Computer Use AgentsClear

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

16 Aug 2026

Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce…

Computer Use Agents Reinforcement Learning

850.2/h

Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments

25 Aug 2026

GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-ups to action misuse, yet existing benchmarks lack systematic evaluation of agent robustness against runtime anomalies.

Computer Use Agents Reinforcement Learning

40.1/h