๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Alex Krentsel
@AlexKrentsel
Autonomous Systems PhD @Berkeley_EECS, Sr Researcher @GoogleResearch. systems guy working on harness-layer self-improvement
๊ฐ€์ž… March 2022
251 ํŒ”๋กœ์ž‰ ์ค‘    4.2K ํŒฌ
Agent harnesses are usually hand-tuned, or optimized offline against benchmarks. What if an agent could improve its own harness *while doing the work*? Introducing Exo, a harness architecture for runtime self-improvement ๐Ÿงต (paper:
๋” ๋ณด๊ธฐ