arXiv:2606. 05342v1 Announce Type: new Abstract: AI agents are increasingly asked to carry out work that spans minutes, hours, or longer.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 08392v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents that interact with the web through browsers.
arXiv:2604. 08523v2 Announce Type: replace-cross Abstract: AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites?
arXiv:2506. 01952v2 Announce Type: replace-cross Abstract: Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent and general framework for automating web-based tasks.
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.
arXiv:2606. 16748v1 Announce Type: new Abstract: Current benchmarks for computer-use agents evaluate models in impersonal environments.
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments.