2 papers
cs.AI2026
OrchSLM: Probing the Dynamics of Small Language Model Orchestration
Chengxi Zhang, Yu Yao
Although large language models (LLMs) have demonstrated remarkable capabilities, their reliance on cloud-scale infrastructure poses fundamental challenges for deployment in agentic…
cs.AI2026
AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning
Hanjun Luo, Qiushi Liu, Jingya Zhang +8
Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-siz…