Jiale Liu

Experience

• Adobe Research · Research Scientist Intern

  05/2025 - 08/2025

  Multi-agent intelligence for creative support.

Publications

(* equal contribution)

• 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
  EMNLP Findings
• 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
  EMNLP
• 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.
  ICML Spotlight

• 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
  COLM Workshop
• 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
  COLM ICLR Workshop Best Paper Award
• Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
  Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Tongliang Liu
  ICML Spotlight
• 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
  ICML
• 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
  ICLR
• 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
  NeurIPS Workshop
• Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction
  Xiaobo Xia, Xiaofeng Liu, Jiale Liu, et al.
  Nexus
• 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
  J-BHI

• 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
  ICLR

Open Source

• AutoGen

  Co-creator and maintainer. An open-source framework enabling next-gen LLM applications via multi-agent conversation.

• AG2

  Co-creator and maintainer. The evolution of AutoGen with integrated adaptive team building for LLM agents.

• FLAML

  Maintainer. A fast library for automated machine learning and tuning.