Microsoft paper: coding agent optimizing prompts from logs beats GEPA at ~$1.60
rohanpaul_ai · x · 2026-10-02
A Microsoft paper introduces CASD (Coding-Agent Skill Distillation): hand your agent's saved logs to an ordinary coding agent, which writes analysis code to find systematic failure modes and distill an optimized prompt — no iterative search needed. It beats prompt-tuning tool GEPA on 3 of 4 agent benchmarks at roughly $1.60 per prompt. Practical takeaway: mine your existing logs first, save trial-and-error tuning for marginal gains.
Related event: Microsoft Paper Shows Coding Agents Are Strong Prompt Optimizers(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a token-efficiency tradeoff — MandeepKaur9407 · 2026-11-16
- sessionwiki turns your past coding-agent sessions into a searchable local wiki for agents — Cold_Past7184 · 2026-11-16
- Developer hits 700+ commits/day with AI, asks how to manage parallel agent work — blixt · 2026-11-16
- Alibaba's G-CAST: governed continual self-training keeps e-commerce agents fresh in production — Yuechun Yu · 2026-11-16
- harness-evals: open-source library to compare agent versions with success-vs-cost plots — slavadubrov · 2026-11-16
- Developers poll real costs of running coding agents on remote VMs for work — radim11 · 2026-11-16