[dead]
HyperAgents: Self-referential self-improving agents
71–80 of 117 posts
Re: HyperAgents: Self-referential self-improving agents
#72The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on oth…
[dead]
Re: HyperAgents: Self-referential self-improving agents
#73The loop on this is basically tweak your prompt until you score better on a contrived test.
The above comment needs to be higher.
IF we had a black box programing language, and handed it over to this system, it would never be able to do anything with it past its context window.
Hey kids I hear you like agents, so we made an agent write agents till we got better agents.
Re: HyperAgents: Self-referential self-improving agents
#74Earlier quoted context omitted.
The most important part of engineering is problem-solving, which feedback loops don't necessarily do. The reason we are here as engineers is: 2.5 billion years ago, the earth made cyanobacteria, which flourished, then flooded the earth with toxic oxygen, killing almost all life on the planet. The initial feedback loop didn't solve a problem, it destroyed a use case. That's not a solution to a problem that an engineer…
This process worked so spectacularly well that it eventually created human consciousness and the very concept of engineering... but I would never design a system that way because it killed version 1.0.
Give hydrogen a few billion years and it starts wondering where it came from, and how it'd make v 2.0 better :)
Re: HyperAgents: Self-referential self-improving agents
#75Can someone add this to OpenClaw :)
My brother in Christ it's 2026, just ask an AI to do it for $10 in API credits.
Re: HyperAgents: Self-referential self-improving agents
#76The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on oth…
Agents need the ability to code but also to objectively and accurately evaluate whether changes resulted in real improvements. This requires skills with metrics and statistics. If they can make those reliable then self-improvement is basically assured, on a long enough timeline.
This is how hyperagents work. They Have the ability to measure improvement in both the meta agent and task agents. There approach requires task agents to tackle tasks that can be empirically evaluated.
Re: HyperAgents: Self-referential self-improving agents
#77The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on oth…
IF they are self modifying. Is there also a big risk, that they cause a bug, to dumb themselves down, break themselves. How do they get back? Are they able to restore a backup of themselves, if a self modification is bad. Or, are there two. One is modifying the other, observing results, before self applying.
Yes this is how hyperagents work. They keep track of their different attempts to see which results in success. It does require tasks that can be measured.
Re: HyperAgents: Self-referential self-improving agents
#78Sigh, as someone who does research in this area, this paper and its promotion on X has so many hype terms it is almost off-putting. If you read the paper what they are doing is trying to modify the scaffolding around a frozen FM until they get something better. None of this obviously includes any training (change to weights) or the underlying architecture. Even for scaffolding, a lot is still human-scaffolded: the outer loop (parent selection, evaluation protocol, task distribution) is mostly fixed. They experimented with editing parent selection and it rediscovers heuristics like UCB/softmax, but doesn’t yet beat handcrafted versions, so a lot of metrics are incremental, which is okay, that is what research is often. But it's not like a run away self-improvement or "improve forever" that people spin online.
It is an extension of their DGM paper. Also it's ~88M+ tokens per full run I think, not surprising as any sort of exploratory search is expensive and I commend them for releasing the code online because it pushes this small subfield. But people need to temper their expectations. IMO the best part is a nice transfer between improvement objectives after exhaustive iteration that they found. I am wondering if what we have here is a way to exhaust local search space, by letting the model better express it.
On a separate one thing I think a lot about is whether these unchecked hyped claims and terms and marketing of papers actually does more bad than good to the field by setting expectations that cannot be delivered and distracting from the actual hard and unsexy nature of problems that need to be solved.
Re: HyperAgents: Self-referential self-improving agents
#79The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on oth…
[flagged]
Re: HyperAgents: Self-referential self-improving agents
#80The loop on this is basically tweak your prompt until you score better on a contrived test.
If true, this is essentially what Dspy does https://github.com/stanfordnlp/dspy (it was made back in 2023)