127 upvotes · 25 AUG 2026 · Liangcai Su, Zhaopeng Feng, Zhuo Chen et al.
This paper introduces FrontierChallenge, a benchmark to evaluate the completion of end-to-end scientific workflows, and investigates the performance of various models in completing these workflows. Practitioners might care about this research to improve the accuracy of scientific workflow completion evaluations.
86 upvotes · 2 NOV 2026 · Jiajie Jin, Guanting Dong, Chengjun Pan et al.
This paper introduces CoworkOS, a system that enables human-AI collaboration in real-world automation tasks, allowing humans and agents to work together on complex tasks like software development and design. Practitioners might care about this paper because it presents a potential solution for scaling agent coworkers to tackle long-horizon tasks.