Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Autogen: Enable next-gen large language model applications

github.com

Post reply on HN
Print view View original

1–10 of 59 posts

Re: Autogen: Enable next-gen large language model applications

#4

Post by h4kor »

A question for people researching LLMs and their capabilities:

Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model?

I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all are "just guessing" what the most probable next token is.

Re: Autogen: Enable next-gen large language model applications

#5

Post by lelag »

h4kor wrote: post #4

A question for people researching LLMs and their capabilities: Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model? I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all a…

Since a single inference is limited by context length, a multiple agents model is able to process more context at each steps of the reasoning chain, which might improve the overall quality. However, given how easy it is getting to fine tune models, it's likely that multi-agent models will make a lot of sense to split the workload and assign each part to a specialized agent.

Re: Autogen: Enable next-gen large language model applications

#6

Post by famouswaffles »

h4kor wrote: post #4

A question for people researching LLMs and their capabilities: Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model? I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all a…

https://arxiv.org/abs/2307.07924

at the very least, you can get things done that would be extremely difficult or practically impossible to do with a single instance.

Re: Autogen: Enable next-gen large language model applications

#8

Post by lachlan_gray »

h4kor wrote: post #4

A question for people researching LLMs and their capabilities: Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model? I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all a…

In a way it is the same thing, agents are mostly an abstraction that make it easier to know what’s going on.

I think of agents more or less as python classes with a mixture of natural language and code functions. You design them to do something with information they produce, and to interface with other agents or “tools” in some way.

But all the agents can be the same language model under the hood, they are frames used to build different kinds of contexts.

And yes I think the idea is that emergent behaviour can be useful. This comes to mind

https://github.com/MineDojo/Voyager

But I think we are still a small ways off from being really smart about agents. My opinion is that we haven’t quite figured out what we are doing yet.

Post reply on HN