Lan-Zhe Guo
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifies the long-term reliability of TTA.
This paper introduces OpenAgent, a problem setting for diagnosing the impact of distributional shifts on Large Language Model agents, and proposes Perturbation-Augmented Fine-Tuning as a solution.
Papers
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
Song-Lin Lv, Weiming Wu, Rui Zhu, Zi-Jian Cheng +1 more
This paper introduces OpenAgent, a problem setting for diagnosing the impact of distributional shifts on Large Language Model agents, and proposes Perturbation-Augmented Fine-Tuning as a solution.