LifeSearch benchmark tests deep research agents on real-life tasks
An arXiv preprint introduces LifeSearch, a benchmark for deep research agents built on 203 Chinese and English tasks drawn from real-user query seeds across 7 life and productivity domains. The authors say they used more than 4,500 hours of human annotation to write over 4,000 fine-grained rubrics, and tested 12 advanced deep research agents under a unified evaluation harness. They report that the best-performing frontier agent, GPT-5.6 Sol, scored only 63.4%, and that aggregate benchmark scores aligned strongly with human judgments (Spearman ρ=0.89, Kendall τ=0.81).
The authors say existing benchmarks focus mainly on academic or synthetic tasks, leaving real-world life and professional productivity settings insufficiently evaluated.
Computer Science > Artificial Intelligence
arXiv:2610.18092 (cs)
[Submitted on 13 Oct 2026]
Title:LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Authors:Yibo Wang, Senjie Jin, Yansong Ning, Xinbing Liang, Haotian Luo, Jiazheng Zhang, Yuxuan He, Will Wu, Clarenceai
View a PDF of the paper titled LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity, by Yibo Wang and 8 other authors