collaborators

7 papers

cs.AI2026

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

Rafal Kocielnik, Pengrui Han, Peiyang Song +5

Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work docum…

cs.AI2026

Human agency in initial human-AI proof formalization workflows

Katherine M. Collins, Simon Frieder, Jonas Bayer +14

For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been…

cs.AI2026

Interactive Evaluation Requires a Design Science

Keyang Xuan, Peiyang Song, Pan Lu +10

AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other…

cs.AI2026

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi +31

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learnin…

cs.AI2026

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Pengrui Han, Xueqiang Xu, Keyang Xuan +12

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely…

cs.AI2026

Large Language Model Reasoning Failures

Peiyang Song, Pengrui Han, Noah Goodman

Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reason…