arXivShuhan Xue, Zixin Ding, Yichen Shen, Yinjie Wang, Zhenfei Yin, Yingcheng Wu, Yuxin Chen, Mengdi Wang, Ling YangTue, Aug 4, 2026, 10:58 AM PDT
score 17.1
New benchmark tests whether AI assistants improve from past experience
Original: PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Source: arxiv.org ↗
Writing ELI5 summary…