Dan Klein

Full Professor, University of California, Berkeley

Joined

December 2017

Names

Dan Klein

Emails

****@cs.berkeley.edu (Confirmed)

****@berkeley.edu (Confirmed)

Personal Links

Homepage

Semantic Scholar

Career & Education History

Full Professor

University of California, Berkeley (berkeley.edu)

2004 – Present

Technical Fellow

Microsoft (microsoft.com)

2018 – 2021

PhD student

Stanford University (stanford.edu)

1999 – 2004

Advisors, Relations & Conflicts

Coauthor

Dave Golland

2013 – 2013

Coauthor

trevor darrell

2013 – 2013

PhD Advisor

Chris Manning

2001 – 2005

Expertise

NLP

2004 – Present

Publications

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alex Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
- ICLR 2026 Oral
- Readers: Everyone
Scalable Evaluation of Language Models with Generated Games
Vivek Verma, David Huang, William Chen, Dan Klein, Nicholas Tomlin
- Submitted to ICLR 2026
- Readers: Everyone
Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs
Noah Ziems, Dilara Soylu, Lakshya A Agrawal, Isaac Miller, Liheng Lai, Chen Qian, Kaiqiang Song, Meng Jiang, Dan Klein, Matei Zaharia, Karel D'Oosterlinck, Christopher Potts, Omar Khattab
- Submitted to ICLR 2026
- Readers: Everyone
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alex Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
- FoRLM 2025
- Readers: Everyone
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
- NeurIPS 2025 LLM Evaluation Workshop Poster
- Readers: Everyone
Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs
Noah Ziems, Dilara Soylu, Lakshya A Agrawal, Isaac Miller, Liheng Lai, Chen Qian, Kaiqiang Song, Meng Jiang, Dan Klein, Matei Zaharia, Karel D'Oosterlinck, Christopher Potts, Omar Khattab
- FoRLM 2025
- Readers: Everyone
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
- NeurIPS 2025 Datasets and Benchmarks Track spotlight
- Readers: Everyone
Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding
Chancharik Mitra, Abrar Anwar, Rodolfo Corona, Dan Klein, Trevor Darrell, Jesse Thomason
- NAACL 2024
- Readers: Everyone
American Sign Language Handshapes Reflect Pressures for Communicative Efficiency
Kayo Yin, Terry Regier, Dan Klein
- ACL 2024
- Readers: Everyone
Diagnostic Uncertainty: Teaching Language Models to Describe Open-Ended Uncertainty
Brian Sui, Jessy Lin, Michelle Li, Anca Dragan, Dan Klein, Jacob Steinhardt
- BuildingTrust
- Readers: Everyone

View all 176 publications

Co-Authors

View all 152 co-authors