2 papers
cs.LG2026
ROAST: Rollout-based On-distribution Activation Steering Technique
Xuanbo Su, Hao Luo, Yingfang Zhang +1
Activation steering provides parameter-efficient control over large language models (LLMs) at inference time, but many methods rely on off-distribution supervision and discrete mas…
cs.CL2026
Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation
Xuanbo Su, Yingfang Zhang, Hao Luo +2
With the growing adoption of Large Language Model (LLM) agents in persistent, real-world roles, they naturally encounter continuous streams of tasks and inevitable failures. A key…