# A senior Google engineer just dropped a 19-page PDF on "Loop Engineering" for LLM and a...
Canonical: https://social-archive.org/yena/OSKTzNkyeD
Original URL: https://x.com/0xMovez/status/2069500921382326531
Author: Movez
Platform: x
## Content
## 1 A senior Google engineer just dropped a 19-page PDF on "Loop Engineering" for LLM and agentic systems. Act → Observe → Learn → Repeat • Act: the LLM proposes a code transformation (tile this loop, parallelize that one). • Observe: a compiler runs it and reports back - is it valid? faster? slower? by how much? • Learn: the LLM reads that feedback and adjusts its next move. • Repeat until it stops finding improvements. The agent gets smarter purely from grounded feedback inside its own context window. This 19-page PDF totally changed the way I’m building agentic systems today. Read it now, then explore the article below. {{IMAGE_0}} {{IMAGE_1}} --- ## 2 https:// arxiv.org/pdf/2511.00592 https://t.co/1h8DPVDUDl