If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, …

If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, 17 real tasks from 3 repositories, with context-injection strategy as the only variable. Correctness does not move on either agent. Equivalence testing bounds any effect to at most 10 to 15 percentage points. A failure-mode triage explains why. Agents fail on implementation skill, feature design, pattern selection and exact wiring, rather than on repository knowledge a markdown file could supply. A manipulation probe confirms it, since the real AGENTS.md never converted a near-miss into a pass on either agent. Borderline task difficulty is agent-specific with Spearman rho of 0.75, so single-agent studies draw tasks from different informative bands and reach opposite conclusions. That explains a lot of the contradictory prior evidence. Paper: https://arxiv.org/abs/2607.27250 Track more trending AI papers in our academy: https://academy.dair.ai/

Related

• Great technical paper from Google. Great read on why context beats scale for agents working against unfamiliar APIs. (bookmark it) GPU kerne…
• New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Age…
• // The Efficiency Frontier // Cool paper on context management. As agents reuse the same documents and histories across many turns, the chea…
• I built an open-source multi-agent SDLC harness that beats a cold Claude Code run on large repos, by learning the repo once. Real benchmarks (incl. where it loses) inside. [P]
• // The Harness Effect // (bookmark it) Now more that ever pay very close attention to the orchestration harness and its effect on costs and …

Source: DAIR.AI (X) | 2026-08-01