Linbo Liu

Research Scientist

AWS AI · Santa Clara, CA

I am a Research Scientist at AWS AI in Santa Clara, working on agent post-training, continual learning, and harness optimization. I lead long-horizon agentic reinforcement learning for large-scale coding agent, benchmark and RL environment curation, and design continual learning and recursive self-improvement algorithms for efficient online adaptation at scale.

I completed my Ph.D. in Statistics at UC San Diego, advised by Professor Danna Zhang and Professor Lily Weng. Before that, I received my Master degree in Statistics from the University of Pennsylvania, supervised by Professor Weijie Su.

My research aims to make AI agents more capable and reliable in the real world. I approach this from several angles: learning from experience at scale, optimizing the agent's context and harness, and making models robust to distribution shift and adversarial inputs.

Education

  • 2018 – 2022

    Ph.D. in Statistics

    University of California San Diego

  • 2016 – 2018

    M.S. in Statistics

    University of Pennsylvania

  • 2012 – 2016

    B.S. in Applied Mathematics

    Tongji University

Recent News

New blog post is out Continual Learning via Real-Time RL for Agents

Can an agent keep learning after deployment, directly from real production-style interactions where each interaction usually gives only one trajectory?

New blog post is out Training a Frontier Java Code Migration Agent with AWS AgentCore Runtime

We train Qwen3-Coder-30B-A3B using AgentCore Runtime integration to outperform Claude 4.5 Haiku on long-horizon Java repo migrations.

New blog post is out Introducing Harness Optimizer: Automatically optimize your agent harness

Tuning the agent harness itself — system prompts, tool descriptions, skills, and advisor models — from collected rollout trajectories.

Website out MigrationBench Website

MigrationBench is a large-scale benchmark for repository-level code migration from Java 8 to long-term support versions such as Java 17/21. It also provides an automated and robust framework for evaluating code migration success at the repository level.

Paper accepted at KDD 2026 MigrationBench: Repository-Level Code Migration Benchmark from Java 8

To appear in the Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining.

Blog

Continual Learning via Real-Time RL for Agents

Can an agent keep learning after deployment, directly from real production-style interactions where each interaction usually gives only one trajectory?

Training a Frontier Java Code Migration Agent with AWS AgentCore Runtime

We train Qwen3-Coder-30B-A3B using AgentCore Runtime integration to outperform Claude 4.5 Haiku on long-horizon Java repo migrations.

Introducing Harness Optimizer: Automatically optimize your agent harness

Tuning the agent harness itself — system prompts, tool descriptions, skills, and advisor models — from collected rollout trajectories.

Amazon introduces two benchmark datasets for evaluating AI agents’ ability on code migration

Announcing MigrationBench and Poly-MigrationBench, which extends repository-level migration beyond Java to .NET Framework, Node.js, and Python.

Open Source Projects

MigrationBench

A large-scale, repository-level code migration benchmark from Java 8 to long-term support versions (Java 17/21), with a comprehensive evaluation framework. Ships an RL training recipe and environment on AgentCore for scalable agentic RL training.

AgentCore RL Toolkit

Turns Bedrock AgentCore into a scalable rollout engine for agentic reinforcement learning, integrating with major RL frameworks such as veRL, Tinker, and Slime.

Harness Optimizer

A framework for flexible harness optimization via customizable objectives, supporting system prompt optimization, tool description optimization, skill creation, and advisor model optimization.

Selected Publications

See also Google Scholar

Preprints

CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection

Linbo Liu, Guande Wu, Han Ding, Yawei Wang, Qiang Zhou, Yuzhe Lu, Zhichao Xu, Huan Song, Panpan Xu, Lin Lee Cheong

arXiv preprint arXiv:2604.07487, 2026

LLM Agents Already Know When to Call Tools – Even Without Reasoning

Chung-En Sun, Linbo Liu, Ge Yan, Zimo Wang, Tsui-Wei Weng

arXiv preprint arXiv:2605.09252, 2026

The Cold-Start Safety Gap in LLM Agents

Chung-En Sun, Linbo Liu, Tsui-Wei Weng

arXiv preprint arXiv:2606.07867, 2026

QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks

Yaojie Hu, Qiang Zhou, Qihong Chen, Xiaopeng Li, Linbo Liu, Dejiao Zhang, Amit Kachroo, Talha Oz, Omer Tripp

arXiv preprint arXiv:2501.17167, 2025

High-dimensional Simultaneous Inference on Non-Gaussian VAR Model via De-biased Estimator

Linbo Liu, Danna Zhang

arXiv preprint arXiv:2111.01382, 2021

Conference & Journal Papers

MigrationBench: Repository-Level Code Migration Benchmark from Java 8

Linbo Liu, Xinle Liu, Qiang Zhou, Lin Chen, Yihan Liu, Hoan Nguyen, Behrooz Omidvar-Tehrani, Xi Shen, Jun Huan, Omer Tripp, Anoop Deoras

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026

Enhancing Language Model Agents using Diversity of Thoughts

Vijay Lingam, Behrooz Omidvar Tehrani, Sujay Sanghavi, Gaurav Gupta, Sayan Ghosh, Linbo Liu, Jun Huan, Anoop Deoras

The Thirteenth International Conference on Learning Representations (ICLR), 2025

Reasoning and Planning with Large Language Models in Code Development

Hao Ding, Ziwei Fan, Ingo Guehring, Gaurav Gupta, Wooseok Ha, Jun Huan, Linbo Liu, Behrooz Omidvar-Tehrani, Shiqi Wang, Hao Zhou

Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024

CodeFort: Robust Training for Code Generation Models

Yuhao Zhang, Shiqi Wang, Haifeng Qian, Baishakhi Ray, Zijian Wang, Linbo Liu, Mingyue Shang, Anoop Deoras, Murali Krishna Ramanathan

Findings of the Association for Computational Linguistics: EMNLP 2024

Promoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches

Linbo Liu, Trong Nghia Hoang, Lam M. Nguyen, Tsui-Wei Weng

23rd IEEE International Conference on Data Mining (ICDM), 2023

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson, Jun Huan

The Eleventh International Conference on Learning Representations (ICLR), 2023

Mentorship

Interns at AWS

Graduate Students at UCSD