Jiale Liu

I am a Ph.D. student in Informatics at Penn State University, advised by Qingyun Wu, and a co-creator and maintainer of AutoGen. In 2026, I was a Student Researcher at Google DeepMind in New York, working on continual learning and memory mechanisms for LLM agents that learn from experience. In Summer 2025, I interned at Adobe Research, where I developed multi-agent systems for open-ended collaborative and creative workflows. Before Penn State, I obtained my B.Eng. in Computer Science from Xidian University, ranking first in my class of 134.

My research develops scalable frameworks and algorithms that enable LLM agents to reason, collaborate, and self-improve in complex, open-ended environments. In particular, I study how to debug and optimize agentic behavior and how to form effective multi-agent teams.

Portrait of Jiale Liu
2027 Job Market

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 – Oct 2026

    Google DeepMind Student Researcher, New York, NY

    Continual learning and memory for LLM agents that learn from experience.

    Mentors: Zun Li, John Schultz

  • May – Aug 2025

    Adobe Research Research Scientist Intern, San Jose, CA

    Multi-agent intelligence for creative support.

    Mentors: Victor S. Bursztyn, Saayan Mitra

Publications

* equal contribution
  1. arXiv 2026

    Learning In-Context Adaptivity for LLMs through Continual Gameplay

    Jiale Liu, Zun Li, John Schultz

    TL;DR We post-train LLMs with trajectory-level RL to excel at learning from memory in repeated poker—our 9B policy boosts experience gain up to 5x over SFT on unseen opponents and matches or surpasses frontier models across 35 opponents.

  2. NeurIPS E&D 2026

    Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?

    Jiale Liu, Huajun Xi, Shaokun Zhang, Yifan Zeng, Tianwei Yue, Chi Wang, Jian Kang, Qingyun Wu, Huazheng Wang

    TL;DR We build a 12,326-trajectory multimodal benchmark across 26 datasets with controlled failure injection, showing frontier LLMs frequently confuse failure symptoms with root causes.

  3. ACL 2026

    TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems

    Jiale Liu, Victor Bursztyn, Lin Ai, Haoliang Wang, Sunav Choudhary, Saayan Mitra, Qingyun Wu

    TL;DR We propose a multi-agent framework that pairs each team member with a preference-conditioned proxy agent, surfacing disagreements through structured discussion to synthesize higher-consensus creative deliverables.

  4. ICML 2026

    Digital Agents Require Unified Agent-Native Environments

    Yiran Wu*, Jiale Liu*, Jieyu Zhang, Yaolun Zhang, Shilong Liu, Chi Wang, Mengdi Wang, Huazheng Wang, Qingyun Wu

    TL;DR We propose agent-native computers and build AgentVM, unifying GUI and programmatic text actions over shared OS state for general-purpose digital agents.

  5. EMNLP Findings 2025

    Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale

    Jiale Liu, Yifan Zeng, Shaokun Zhang, Chi Zhang, Malte Højmark-Bertelsen, Marie Normann Gadeberg, Huazheng Wang, Qingyun Wu

    TL;DR We propose a divide-optimize-merge framework for scalable LLM agent optimization, improving benchmark accuracy while cutting prompt token consumption by 56%.

  6. EMNLP 2025

    SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement

    Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, Zhenwen Shao, Qingyun Wu, Huazheng Wang

    TL;DR We build a lightweight multimodal document QA framework combining dual-cue page retrieval with iterative VLM working-memory refinement, boosting accuracy while reading fewer pages.

  7. ICML 2025 Spotlight

    Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

    Shaokun Zhang, Ming Yin, Jieyu Zhang, Jiale Liu, et al.

    TL;DR We are the first to formalize automated failure attribution for multi-agent systems with an annotated benchmark spanning 127 systems, exposing how poorly frontier reasoning models localize decisive error steps.

  8. COLM Workshop 2024

    Adaptive In-conversation Team Building for Language Model Agents

    Linxin Song*, Jiale Liu*, Jieyu Zhang, Shaokun Zhang, Ao Luo, Shijian Wang, Qingyun Wu, Chi Wang

    TL;DR We build Captain Agent, which dynamically recruits and reflects on nested multi-agent teams per subtask, improving accuracy by 21.9% without task-specific prompt engineering.

  9. COLM 2024 ICLR Workshop Best Paper Award

    Autogen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

    Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang

    TL;DR We build AutoGen, an open-source multi-agent conversation framework enabling customizable, conversable LLM agents across coding, research, and tool-use workflows.

  10. ICML 2024 Spotlight

    Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

    Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Tongliang Liu

    TL;DR We are the first to formalize minimal-size coreset selection under explicit model performance constraints, providing an optimization algorithm with theoretical convergence guarantees.

  11. ICML 2024

    Offline Training of Language Model Agents with Functions as Learnable Weights

    Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu

    TL;DR We propose treating external agent tools as learnable parameters via AgentOptimizer, iteratively forging and refining functions from execution traces without updating LLM weights.

  12. ICLR 2024

    IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

    Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu

    TL;DR We propose framing selective annotation for in-context learning as graph influence maximization, selecting high-coverage demonstrations with lower annotation cost and submodular guarantees.

  13. NeurIPS Workshop 2024

    Embodied LLM Agents Learn to Cooperate in Organized Teams

    Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L Griffiths, Mengdi Wang

    TL;DR We propose prompt-based organizational structures and a Criticize-Reflect evolution loop for embodied multi-agent teams, cutting communication overhead and boosting efficiency by up to 30%.

  14. Nexus 2024

    Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction

    Xiaobo Xia, Xiaofeng Liu, Jiale Liu, et al.

    TL;DR We build a systematic trustworthiness benchmark exposing reliability and robustness challenges of deep learning models for continental-scale water quality prediction.

  15. J-BHI 2024

    RLAD: A Reliable Hippo-guided Multi-task Model for Alzheimer's Disease Diagnosis

    Zhenxin Lei*, Wenjing Zhu*, Jiale Liu*, Cong Hua, Johann Li, Syed Afaq Ali Shah, Liang Zhang, Mohammed Bennamoun, Cuiping Mao

    TL;DR We propose a hippocampus-guided multi-task deep learning framework for reliable Alzheimer's disease diagnosis from neuroimaging.

  16. ICLR 2023

    Moderate Coreset: A Universal Method of Data Selection for Real-world Data Analysis

    Xiaobo Xia, Jiale Liu, Jun Yu, Xu Shen, Bo Han, Tongliang Liu

    TL;DR We propose selecting training examples near the median distance to class centers, yielding a simple and distribution-robust coreset baseline across diverse real-world settings.

Open Source

  • Co-creator, Maintainer
    AutoGen microsoft/autogen

    An open-source framework enabling next-gen LLM applications via multi-agent conversation.

  • Co-creator, Maintainer
    AG2 ag2ai/ag2

    The evolution of AutoGen with integrated adaptive team building for LLM agents.

  • Maintainer
    FLAML microsoft/FLAML

    A fast library for automated machine learning and tuning.