TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Kan Zhu Mathew Jacob Chenxi Ma Yi Pan Stephanie Wang Arvind Krishnamurthy Baris Kasikci
作者信息
Abstract
Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge requires understanding real workload patterns, yet the data needed for such analysis is largely absent. Existing public traces and benchmarks do not capture real, day-to-day coding-agent usage across multiple agents and model families for serving-system analysis. To help fill this gap, we collect and release a trace of roughly 4,300 coding-agent sessions, containing about 350,000 LLM steps and 430,000 tool calls from our own day-to-day use of Claude Code and Codex. Our analysis shows that coding-agent workloads feature long autonomous loops, long contexts with short outputs, diverse and heavily-tailed tool calls, and high but imperfect prefix cache hit rates. These findings point to concrete opportunities for optimizing serving, including lower-overhead tool calling, append-length-aware prefill, semantic-aware tool-latency prediction, and improved KV-cache management around human-paced gaps. We release the dataset, trace collection pipeline, and analysis code at https://github.com/uw-syfi/TraceLab.git the project website is https://tracelab.cs.washington.edu.引用本文复制引用
Kan Zhu,Mathew Jacob,Chenxi Ma,Yi Pan,Stephanie Wang,Arvind Krishnamurthy,Baris Kasikci.TraceLab: Characterizing Coding Agent Workloads for LLM Serving[EB/OL].(2026-06-30)[2026-07-03].https://arxiv.org/abs/2606.30560.学科分类
计算技术、计算机技术
|国家预印本平台