按年被提到
20262026 · 5 次2026
强化学习与智能体›大模型智能体·arXiv:2603.19461 · cs.AI

Hyperagents

Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 5 人首次 2026-03-23 · 最近 2026-05-23
5不同的人
2活跃月份
4讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce \textbf{hyperagents}, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论pegasus · 2026-03

“There's a paper at https://arxiv.org/abs/2603.19461 Abstract: Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. Th…”

HyperAgents原评论 ↗
评论NitpickLawyer · 2026-03

“The 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 capabilit…”

HyperAgents原评论 ↗
被提交为 story · 3 次