AgentConnect study finds coding agents often choose grep over LSP
Pengcheng Xu's preliminary study found that tool choice followed the task, while location-only LSP results increased follow-up reads and token use.
By RuntimeWire Staff · Published
Primary source: AgentConnect
Why it matters
Coding-agent performance depends on the complete tool loop. Replacing a native search path with a cleaner abstraction can increase token use and lower success if the output creates extra work.
Pengcheng Xu, author of AgentConnect's coding-tool study, found that coding agents defaulted to grep on symbol-named localization tasks even when semantic navigation was available. Their choices changed with the task, and location-only results from the Language Server Protocol, or LSP, often required extra file reads.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.