SimpleTool: Parallel Decoding for Real-Time LLM Function Calling
arXiv:2603.00030v1 Announce Type: new Abstract: LLM-based function calling enables intelligent agents to interact with external tools and environments, yet autoregressive decoding imposes a fundamental latency …
Xiaoxin Shi, Jiaxin Wan, Linkang Dong, Wei Jiang, Yue Liu, Zengfeng Huang
3 views