Pengrui Lu — accepted AI-conference papers

2026

InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI Research

Yunze Wu, Dayuan Fu, Weiye Si, Zhen Huang, Mohan Jiang, Keyu Li +10

ICLR 2026poster

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-t…

Cited by 0 Source ↗code ↗Scholar ↗

2025

DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu +1

EMNLP 2025

Large Language Models (LLMs) with web search capabilities show significant potential for deep research, yet current methods—brittle prompt engineering or RAG-based reinforcement learning in controlled environments—fail to capture real-world complexities. In this paper, we introduce DeepResearcher, t

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗