按年被提到
20252026 · 2 次2026
强化学习与智能体›大模型智能体·arXiv:2510.12066 · cs.AI

AI Agents as Universal Task Solvers

Alessandro Achille, Stefano Soatto · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-02-25 · 最近 2026-04-16
2不同的人
2活跃月份
2讨论串
1被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture its algorithmic structure so as to reduce the time needed to solve new tasks. In this view, information from past experience serves not only to reduce a model's uncertainty - as in Shannon's classical theory - but to reduce the computational effort required to find solutions to unforeseen tasks. Working in the verifiable setting, where a checker or reward function is available, we establish three main results. First, we show that the optimal speed-up on a new task is tightly related to the algorithmic information it shares with the training data, yielding a theoretical justification for the power-law scaling empirically observed in reasoning models. Second, while the compression view of learning, rooted in Occam's Razor, favors simplicity, we show that transductive inference yields its greatest benefits precisely when the data-generating mechanism is most complex. Third, we identify a possible failure mode of naive scaling: in the limit of unbounded model size and compute, models with access to a reward signal can behave as savants - brute-forcing solutions without acquiring transferable reasoning strategies. Accordingly, we argue that a critical quantity to optimize when scaling reasoning models is time, whose role in learning has remained largely unexplored.

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js8 · 2026-04

“I recently came across this presentation https://youtu.be/QxkRf-xSfgI, and it changed my view of AI quite significantly. (There is also a paper https://arxiv.org/html/2510.12066v2.) The fundamental idea is that "intelligence" really means trying to shorten the time to figure out something. So it's a tradeoff, not a quality. And AI agents are doing it. …”

Arguing with Agents原评论 ↗
被提交为 story · 1 次