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

Towards a science of scaling agent systems: When and why agent systems work

research.google

Post reply on HN
Print view View original

11–20 of 42 posts

Re: Towards a science of scaling agent systems: When and why agent systems work

#12

Post by CuriouslyC »

zby wrote: post #9
CuriouslyC wrote: post #4

This is a neat idea but there are so many variables here that it's hard to make generalizations. Empirically, a top level orchestrator that calls out to a planning committee, then generates a task-dag from the plan which gets orchestrated in parallel where possible is the thing I've seen put in the best results in various heterogeneous environments. As models evolve, crosstalk may become less of a liability.

Reasoning is recursive - you cannot isolate where is should be symbolic and where it should be llm based (fuzzy/neural). This is the idea that started https://github.com/zby/llm-do - there is also RLM: https://alexzhang13.github.io/blog/2025/rlm/ RLM is simpler - but my approach also have some advantages.

I only agree with that statement if you're drawing from the set of all possible problems a priori. For any individual domain I think it's likely you can bound your analytic. This ties into the no free lunch theorem.

Re: Towards a science of scaling agent systems: When and why agent systems work

#14

Post by zkmon »

> We found that independent multi-agent systems (agents working in parallel without talking) amplified errors by 17.2x

The paper sounds too shallow. The errors data doesn't seem to have a rationale or correlation against the architecture. Specifically, what makes the SAS architecture to have lowest error rates while the similar architecture with independent agents having highest error rates? The conclusion doesn't seem well-grounded with reasoning.

Re: Towards a science of scaling agent systems: When and why agent systems work

#19

Post by verdverm »

nawgz wrote: post #10
verdverm wrote: post #8

Earlier quoted context omitted.

My hunch is that Google is past it's prime, all the good PMs are gone, and now it looks like a chicken hydra with all the heads off and trying to run in multiple directs. There is no clear vision, coherence, or confidence that the products will be around in a another year

Kind of a weird take given they are one of the strongest AI providers who are the most vertically integrated. Sure, maybe the company isn’t as healthy as it once was, but none of them are - late stage capitalism is rotting most foundations

I saying this as a big, but dimming, Google-stan

Their poor product decisions have driven me away, that doesn't mean I'm still very impressed with everything under that. I'm building my custom agent on their open source Agent Development Kit and the Gemini family.

Re: Towards a science of scaling agent systems: When and why agent systems work

#20

Post by kioku »

I found the captions on Figure 1 quite interesting.

> Average performance (%) across four agentic benchmarks improves consistently with increasing model Intelligence Index.

> Centralized and hybrid coordination generally yield superior scaling efficiency, suggesting that collaborative agentic structures amplify capability gains more effectively than individual scaling alone.

Then again, the deltas between SAS and best performing MAS approach are ~8%, so I can't help wonder if it's worth the extra cost, at least for the generation of models that was studied.

Post reply on HN