7 citations · 19 across the 28 of their papers we have counts for
12 papers · 1 filter
StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents
Chuan Zou, Yujun Zhou, Xiaonan Luo +1
Long-horizon coding requires agents to maintain an evolving view of the project they are changing: what problem is currently being solved, what has already been learned or modified…
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
Taicheng Guo, Haomin Zhuang, Kehan Guo +4
Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding strong configurations within…
When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models
Yujun Zhou, Christopher M. Ackerman
Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-spec…
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
Kehan Guo, Yili Shen, Yujun Zhou +4
The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as…
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Yujun Zhou, Kehan Guo, Haomin Zhuang +8
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated…
AIRGuard: Guarding Agent Actions with Runtime Authority Control
Suliu Qin, Haomin Zhuang, Yujun Zhou +2
Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This ma…
AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
Haomin Zhuang, Hanwen Xing, Yujun Zhou +5
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration in…
NARRA-Gym for Evaluating Interactive Narrative Agents
Yue Huang, Yuchen Ma, Jiayi Ye +14
Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limit…
PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models
Han Bao, Penghao Zhang, Yue Huang +9
Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason abou…
AI Alignment Breaks at the Edge
Han Bao, Yue Huang, Xiaoda Wang +5
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that mode…
ProbeLLM: Automating Principled Diagnosis of LLM Failures
Yue Huang, Zhengzhe Jiang, Yuchen Ma +8
Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has…
Alignment Risks from Capability-Seeking RL Training
Yujun Zhou, Yue Huang, Han Bao +8
While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerabl…