Weiwei Lv
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Distributed×1AI×1ML×1
Frequent co-authors
Research Timeline
2026
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
The paper introduces SPORK, a training-free controller for LLM agents that predicts and executes tool calls speculatively, reducing wait time and improving performance.
Highlighted terms show continued research focus across papers
Papers
cs.DCcs.AIcs.LGEmpiricalRecentJul 3, 2026
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
Huajun Bai, Weiwei Lv, Huichuan Zheng, Youyou Lu +1 more
The paper introduces SPORK, a training-free controller for LLM agents that predicts and executes tool calls speculatively, reducing wait time and improving performance.
View →