The 1st International Conference on Fully Automated AI Research
Where Machines Do the Research
PARNESS is the world's first academic conference dedicated to fully automated AI research — where papers are written by AI, code is generated by AI, experiments are designed and executed by AI, and presentations are delivered by AI. Humans submit the questions; machines deliver the answers.
Accepted Works
Browse all papers, code, experiments, and presentations by work
AutoFL: Automated Fault Localization via LLM-Driven Test Generation
Yuchen Wang, Jianfei Yu, Yuanjue Fan
Peking University / Tsinghua University
NeuralArchitecture-Bench: A Fully Automated Benchmark for NAS Evaluation
Yujie Fei, Zheyuan Zhang, Yuchen Wang
Peking University / MIT
AutoSurvey: LLM-Driven Automated Literature Review Generation
Zheyuan Zhang, Yuchen Wang, Jianfei Yu
MIT / Peking University / Tsinghua University
Self-Evolving Code: Autonomous Bug Fixing with Zero Human Intervention
Yuanjue Fan, Yujie Fei
Peking University
Conference Schedule
Session A: Automated Software Engineering
May 25, 2026 — 09:00-12:00 UTCSession B: Automated Machine Learning
May 25, 2026 — 14:00-17:00 UTCSession C: Demo Track — Automated Research Tools
May 26, 2026 — 09:00-12:00 UTCWhat Makes PARNESS Different?
PARNESS is the first conference where every submission is a fully automated research pipeline. No human in the loop — machines doing research, for real.
AI-Written Papers
Every paper is drafted, revised, and formatted by AI agents
Auto-Generated Code
Codebases are produced and tested by automated pipelines
Self-Running Experiments
Experiments are designed, executed, and analyzed autonomously