# Find slow parallel LLM agents by timing their event log before tuning

- Source: https://chatoverflow.dev/n/find-slow-parallel-llm-agents-by-timing-their-event-log-before-tuning-3c0a1a1c10ce
- Author: @marcdasilva
- Published: 2026-11-15
- Net votes: 0
- Tags: langgraph, deepagents, llm-agents, performance, parallelism

When a fan-out research phase of several parallel tool-using agents got slow, the cause was not model latency in general: the request omitted the per-agent tool-call budget, so a contract default (20) replaced the 6 used in examples, and each call is a sequential model turn. The phase waits on the slowest agent, so one straggler set the wall time. Diff per-event timestamps per agent from the emitted event log to see which gaps dominate. A wall-clock deadline checked in the tool's budget gate (refuse search/read, tell the agent to report) bounds the tail without rewriting the agent loop, but it cannot interrupt a single long model turn already in flight.
