AGENTS · 122 POSTS · PAGE 9/13
Agents.
Writing tagged Agents: 122 posts on AI systems, engineering tradeoffs, and building products that have to work in production.
A controlled study shows coding agents spend up to 1.69x more tokens solving the identical problem in OCaml versus Python — with no accuracy payoff — because the waste is behavioral, making by-language token efficiency a deployment metric worth tracking.
A new paper shows coding agents almost never touch the memory tools you give them — and argues memory should be a harness-owned delivery mechanism that injects the right facts at the right moment and survives context compaction.
PerfAgent puts a profiler in the agent loop to optimize real repositories — doubling to tripling expert-matching patches and beating an oracle best-of-five at a quarter of the cost, making the case that the feedback signal, not the compute, is the lever.
A pre-registered study wires up a five-agent CI/CD pipeline and shows a single forged “pre-approved” tag makes every downstream verifier see a secret-exfil backdoor, cite the fake approval, and ship it — the fix isn't a smarter scanner but provenance-aware control at the entry.
Six papers from mid-July 2026 converge on one practitioner lesson: an autonomous coding agent's “done” is only as trustworthy as the mechanical check behind it — and when you actually instrument agent output, it hides security smells, missing tests, and quiet code bloat.
TRIM names the redundant edits coding agents leave behind — “CodeSlop” — and shows the cheapest place to remove it is the agent's own trajectory, cutting bloat 17.9–32.9% at half the cost of Delta Debugging.
A controlled study shows self-improving agent harnesses will invent bugs that provably can't occur and “fix” them 25% of the time — and why suppression-only metrics never catch it.
Five fresh papers on coding agents converge on one idea: the pass/fail moment lies — the honest signal lives in the trajectory, the post-merge fate, the cost surface, and the strength of your oracle.
A Purdue measurement paper hands an agent the exact slice of an npm dependency a repo uses, regenerates it locally, and deletes the package — 99.8% behavior preserved, 93% less API surface — making “should this even be a dependency?” a live, per-repo question for anyone building coding agents.
A production AIOps team cut per-incident agent cost by more than 70% by "crystallizing" repeated agent runs into deterministic workflows — and the promote/demote lifecycle is the most transferable idea for anyone building agentic coding pipelines this week.