Paper Archive

输入关键词搜索 102 篇论文

tracked author

Simran Arora

Coauthor of ThunderAgent. Homepage identifies her as lead of the Frontier Performance research team at Together AI, incoming Caltech CMS assistant professor, and Stanford CS PhD from Hazy Research.

1 archived notes X: high HomepageX

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

Jul 03, 2026

ThunderAgent: A Simple, Fast and Program Aware Agentic Inference System

ThunderAgent 把跨多轮 LLM 调用与工具等待建模为带 phase、status、KV footprint、backend placement 和 tool dependency 的 LLM Program，使 scheduler 能按 Reasoning / Acting 状态控制 KV working set，并在释放 KV 后通过全局队列重新选择恢复节点；论文在所测高并发 tool use serving 与 rol...

2602.13692-thunderagent-program-aware-agentic-inference Agent WorkflowInference SchedulingKV Cache