Releasing a collection of 2,000 papers to test if an LLM agent can learn research taste

ZimingLiu11 · x · 2026-08-23

Ziming Liu released a collection of 2,000 arXiv papers manually curated since 2022 to explore if an LLM agent can learn his research taste. Student Shanbin Yu built an agent to predict 15 papers he would like recently, with manual scoring and detailed comments. This remains a preliminary case study, not a formal benchmark.

Original post →

More from Research

Research channel →