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?
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 16748v1 Announce Type: new Abstract: Current benchmarks for computer-use agents evaluate models in impersonal environments.
arXiv:2608.22510v1 Announce Type: new Abstract: Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: th...
arXiv:2604. 13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments.
arXiv:2609.06059v1 Announce Type: new Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to a...
StartupBench is a new benchmark that evaluates general-purpose agents on end-to-end workflows derived from AI startup products that have proven market adoption. It translates real-world product workflows into deliverable-oriented tasks and assesses them with detailed rubrics. The study finds that even the best models complete only about 30% of these tasks, highlighting challenges such as complex instruction following and domain expertise.
StartupBench is a benchmark that evaluates general‑purpose agents on end‑to‑end workflows derived from real AI startup products that have proven market adoption. It translates these product workflows into deliverable‑oriented tasks and assesses them with detailed rubrics that capture complex requirements. Even the best current models complete only about 30% of the tasks, highlighting failures in instruction following and domain expertise.