LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Monday, 28 September 2026

Coding agents waste up to 22.75% of task budgets

Coding agents repeatedly spend money on redundant retrieval, similar scripts, and rerunning tests, and these behaviors affect 79% to 98% of SWE-bench tasks. The study analyzed 1,200 trajectories, then tested fixes across 10k tasks. Developer-designed skills, meaning reusable high-level guidance, cut costs by up to 41.73%, while structure-aware retrieval sometimes raised costs by 28.14%.

Read the source: arxiv.org ↗In the 28 September issue →