The host argues that ARC-AGI-3, unlike the more abstract ARC-AGI-1/2, centers on 'agency' — having ambitious goals and the planning capacity to realize them — distinguishing it from a merely reactive sense-act loop. ✦ AI generated
Host · Machine Learning Street Talk · 2026-07-01 · original ↗
starts at this moment · 41:47
So agency in my in my definition is the ability of an agent to have goals to plan and realize those goals. And the more ambitious the goals are and the more you realize the goals the more agency you have. So there's a kind of low-level nononsense definition of agency which is just a thing that can sense and act.
verbatim transcript · starts at 41:47
41:47abstract kind of legible way. Now RKGI3 it introduces in my opinion and we can talk about this the concept of agency. So agency in my in my definition is the ability of an agent to have goals to plan and realize those goals. And the more ambitious the goals are and the more you realize the goals the more agency you have. So there's a kind of low-level nononsense definition of
42:12agency which is just a thing that can sense and act. So that's like if I'm doing computer programming that's what an agent is. But the more kind of cognitive science definition of an agent is one that sort of has future pointing control. I have these big goals in the future and I can realize them and that makes me an agent. So I you know I I think that RKGI 3 introduces agency not
42:36just in terms of realizing goals but acquiring goals. Um yes, agency and also like acquiring these goals over time through interaction and adapting them because not only do uh do the levels on their own to be solved require interaction but all the levels change. So these goals dynamically change and you so that you why why you cannot uh learn them learn them directly. Um and then on the on the concept of agency. So
43:04I would I would argue that one of the interesting things that we saw is that what I what I thought coming into this challenge and started working on this problem is that would be difficult for the agent to have any sort of idea what it should be doing at all when it when it solves the when it tries to solve the first level. But I think by now we got
43:25at least one solve on all the public games at least the first level. May it be by trial and error or maybe it be by luck but still there is some somehow LLMs seem to be able to figure out what they need to do. That might be through the different biases that are already encoded for humans that have been building these games. But somehow it is possible to generate these hypothesis.