Authors

Weiqiao Shan

Publications 2

Preprint Open access

Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification

Yingfeng Luo, Shaowei Wei, Daixin Wang et al. · 2026

Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments. Yet how trustworthy such self-verification is remains poorly understood. To investigate this question systematically, we introduce a diagnostic framework that identifie …

Preprint Open access

Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models

Hongjin Song, Runwu Shi, Weiqiao Shan et al. · 2026

Short-to-long training is a simple curriculum for speech models, but its gains can be difficult to interpret. In speech token language models, length-based training can change the shuffle policy, batch composition, token retention, and token weights under batch-mean loss. We disentangle these factors through matched co …

Co-authors