# Microsoft paper reports a 16.6-point average gain for CASD prompt optimization

CASD has an off-the-shelf coding agent analyze a full set of agent logs and write the findings as rules in one prompt, with no environment access or validation data. DAIR.AI says one pass beat GEPA and SkillOpt on the reported benchmarks at about $1.60 per optimized prompt.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:01:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/388582a36261463096d234bf.html

Content language: en
Localization state: sameLanguage

Source: DAIR.AI · Published 9/25/2026, 07:04:51

DAIR.AI describes a [Microsoft paper on coding agents as prompt optimizers](https://academy.dair.ai/papers/coding-agents-are-strong-prompt-optimizers-2609.26261). Its method, CASD, gives an off-the-shelf coding agent the full set of agent logs and has it write the analysis code, instead of running a search loop over small batches of trajectories. The agent computes statistics over the whole trajectory corpus, finds recurring failure modes, reads representative episodes, and writes those findings as rules in one prompt. It needs no environment access and no validation data.

Across ALFWorld, tau2-bench retail and telecom, and Spreadsheet Bench-Verified, one CASD pass improved the unoptimized baseline by 16.6 points on average. GEPA improved it by 10.9 points and SkillOpt by 5.3. Each optimized prompt costs about $1.60, more than 22 times cheaper than validation-gated search.

Tags: Prompt optimization, CASD, Microsoft, Coding agents, Benchmarks

[View original post](https://x.com/dair_ai/status/2103479392106352910)