activity
20242026
most citedJustice or Prejudice? Quantifying Biases in LLM-as-a-Judge

8 citations · 19 across the 21 of their papers we have counts for

collaborators

28 papers

cs.LG2026

Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors

Shiyi Du, Jiayuan Liu, Weihua Du +6

Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We obser…

cs.LG2026

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

Zhenwen Liang, Yujun Zhou, Sidi Lu +3

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homoge…

cs.HC2026

AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents

Haomin Zhuang, Hanwen Xing, Xiangliang Zhang

Recent autonomous AI agents such as Codex, and Claude Code have made it increasingly practical for users to delegate complex tasks, including writing emails, executing code, issuin…

cs.CL2026

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…

cs.LG2026

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs

Yue Huang, Haomin Zhuang, Jiayi Ye +6

Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less us…

cs.CL2026

Reliable Control-Point Selection for Steering Reasoning in Large Language Models

Haomin Zhuang, Hojun Yoo, Xiaonan Luo +2

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behav…