About
I am a Ph.D. student in Informatics at Penn State University, advised by Qingyun Wu. Before Penn State I obtained my B.Eng. in Computer Science from Xidian University, where I ranked first in my class of 134. In summer 2025 I was a research scientist intern at Adobe Research.
My research develops scalable frameworks and algorithms that help LLM agents reason, collaborate, and self-improve in complex, open-ended environments. I study how to debug and optimize agentic behavior, and how to form effective multi-agent teams. I am a co-creator and maintainer of AutoGen.
I am on the job market and looking for full-time roles starting in 2027. If you are hiring, I would love to hear from you. jiale.liu@psu.edu
Experience
-
May – Aug 2025
Research Scientist Intern Adobe Research, San Jose, CA
Multi-agent intelligence for creative support.
Mentored by Victor S. Bursztyn, Saayan Mitra
Publications
Authors marked with an asterisk contributed equally.
2026
-
TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
-
Digital Agents Require Unified Agent-Native Environments
2025
-
Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale
-
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
-
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
2024
-
Adaptive In-conversation Team Building for Language Model Agents
-
Autogen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
-
Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
-
Offline Training of Language Model Agents with Functions as Learnable Weights
-
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
-
Embodied LLM Agents Learn to Cooperate in Organized Teams
-
Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction
-
RLAD: A Reliable Hippo-guided Multi-task Model for Alzheimer's Disease Diagnosis
2023
-
Moderate Coreset: A Universal Method of Data Selection for Real-world Data Analysis
Open source
-
Co-creator and maintainer. An open-source framework enabling next-gen LLM applications via multi-agent conversation.
-
Co-creator and maintainer. The evolution of AutoGen with integrated adaptive team building for LLM agents.
-
Maintainer. A fast library for automated machine learning and tuning.