2 papers
cs.AI2026
Component Replacement in LLM Agents: A Critical Scoping Review of Task Benefit and Attribution
Shuyang Zhang, Jianshuo Chang
Background: Choosing an agent controller and deciding which component to improve require different evidence. A replacement can change both the decision rule and what the agent can…
cs.LG2026
Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
Zhichen Dong, Zhixuan Liu, Yuyu Fan +3
Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effe…