Author

Lin-Na Wu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection

Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or repeat unsuccessful attempts without useful correction. We introduce CoEvoke, a cross-domain framework that evokes these interactions during trajectory collection. Contr...

Lin-Na Wu, Shun-Yu Yao, Yu-Heng Wang et al. · 0 citations

#artificial intelligence Preprint Oct 2026

Collaborative Learning and Reasoning over Model Slices

Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-model reasoning remains vulnerable to error propagation, as later steps depend on the model's earlier outputs, leaving reasoning blind spots difficu...

Yu-Heng Wang, Run-De Yang, Zhu-Han Bao et al. · 0 citations