註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Viv
@Vtrivedy10
applied research @LangChain Labs, prev @awscloud, phd cv @templeuniv
加入 February 2013
1.9K 正在關注    16.9K 粉絲
exo is a really cool project exploring what happens when agents can autonomous self-edit any piece of their harness -> imo this is a form of online continual learning the long-horizon memory aspect of this is interesting - let agents operate autonomously in tons of situations over time - let them self-evolve to solve those tasks - keep a log of what harness configurations help - develop a meta skill of "how do i best edit myself in XYZ situations"
顯示更多
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 🧵 (paper:
顯示更多