More compute made one agent 13x faster, another just 4%: agents' bottlenecks are task-dependent

alex_verem · x · 2026-09-24

A Korea University and Microsoft Research Asia paper measured where agents spend time across RAG QA, web search, and coding tasks. Key findings:

Takeaway: before buying more compute, check what your agent is actually waiting on.

Original post →

More from coding & agent

coding & agent channel →