2 papers
cs.SE2026
Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research
Lezhi Yu, Xiaogang Xu, Yuhua Zhou +2
LLM agents used for scientific experimentation must do more than generate executable code: they must implement the reference method faithfully, design experiments that test the pap…
cs.LG2026
BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference
Yuhua Zhou, Shaoqi Yu, Shichao Weng +4
Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Transformer blocks, but existi…