Google "YouSum Live" 00:00:24 Goal: Achieve long-running complex tasks with large models 00:02:05 Multi-agent workflows enhance task decomposition and specialization 00:02:36 Autogen platform facilitates multi-agent collaboration 00:03:16 Four agents achieved top results on Gaia Benchmark 00:03:28 Doubled performance on the hardest set of questions 00:03:49 Agents follow a structured loop involving tasks delegation 00:04:12 Educated guesses crucial for language model speculation 00:05:13 Future plans include introducing agents for self-improvement Google "YouSum Live"
Could AutoGen be used as the backend for generative agents in more complex simulation environments like AI Town? Might it provide useful abstractions for agent memory, perception, reflection and planning?
all that is one way, agents are working on web resources designed for humans. there needs to be a mirror effort where web resources become agent friendly. also this would ultimately result in scalping for instance so we would need circular lottery systems for all qualifying agents within an interaction quantum
So are we taking things which have been open sourced for a while and turning them into microsoft research? Multi agents has been there for a while, nothing new here! Also honestly seems more of a programming problem than a AI research problem.
![ปฏิเสธไม่ไหว (Crush on you) - LIPTA feat. No One Else [TEASER MV]](http://i.ytimg.com/vi/VC689EgdSIw/mqdefault.jpg)
Discover more about research at Microsoft through our Research Forum Copilot experience: aka.ms/ResearchForumCopilot_YT
complex 0:22 tasks 👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽👏🏽
This levels the playing field for small business. Thank you.
I, for One, Welcome Our Agent Overlords
Beautiful presentation - concise, authentic, to the point.
I didn't know Fernado Alonso is such a great AI researcher.
Nice! This can be turn key to so many businesses!
This is great, thanks for all the good work. That being said, let my man take a nap.
Stop 😂
Is there a notebook / example code of what Adam discussed?
Let’s go Autogen! Keep up the fight.
The presenter here is awesome! Use him more!
Yes a tutorial will be good.
Does RAG is recommended for text documents mainly?
Great work! 👏👏👏
Google "YouSum Live"
00:00:24 Goal: Achieve long-running complex tasks with large models
00:02:05 Multi-agent workflows enhance task decomposition and specialization
00:02:36 Autogen platform facilitates multi-agent collaboration
00:03:16 Four agents achieved top results on Gaia Benchmark
00:03:28 Doubled performance on the hardest set of questions
00:03:49 Agents follow a structured loop involving tasks delegation
00:04:12 Educated guesses crucial for language model speculation
00:05:13 Future plans include introducing agents for self-improvement
Google "YouSum Live"
Could AutoGen be used as the backend for generative agents in more complex simulation environments like AI Town?
Might it provide useful abstractions for agent memory, perception, reflection and planning?
Very nice overview. Thanks!
Do you consider this production ready?
So do we have agents that can look at photos now?
all that is one way, agents are working on web resources designed for humans. there needs to be a mirror effort where web resources become agent friendly. also this would ultimately result in scalping for instance so we would need circular lottery systems for all qualifying agents within an interaction quantum
Amazing! When can we use it?
It's already open source for a year or so. Just Google autogen
My favorite part is the crackhead presentation style 👍
Your comment made me laugh 😀 but I liked the style actually.
So cool
we could just put a human in the loop as the operator so basically
auto gen
So are we taking things which have been open sourced for a while and turning them into microsoft research? Multi agents has been there for a while, nothing new here! Also honestly seems more of a programming problem than a AI research problem.