Llm on R. Calixtohttps://rcalixto.blog/tags/llm/Recent content in Llm on R. CalixtoHugoenSat, 16 May 2026 00:00:00 -0300The Code Agent That Improves With Every Runhttps://rcalixto.blog/posts/ahe-self-improving-agents/Sat, 16 May 2026 00:00:00 -0300https://rcalixto.blog/posts/ahe-self-improving-agents/Reading the AHE paper forced me to rethink where agent improvement really happens. The largest gains did not come from better prompts. They came from memory, tools, and middleware. Here is what that means for real engineering teams.