https://mllog.dev/en/tags/coding-agents/Recent content in Coding-Agents on MLLog.devhttps://mllog.dev/images/default_mllog.pnghttps://mllog.dev/images/default_mllog.pngHugo -- 0.147.9enTue, 09 Jun 2026 08:00:00 +0100https://mllog.dev/en/posts/swe-explore-benchmarking-coding-agents-repository-exploration/Tue, 09 Jun 2026 08:00:00 +0100https://mllog.dev/en/posts/swe-explore-benchmarking-coding-agents-repository-exploration/SWE-Explore isolates repository exploration from patch generation, revealing that coding agents find the right files ~65% of the time but recall only ~15-19% of the lines that actually matter — and that context efficiency predicts downstream resolve rate with Pearson r = 0.950.