按年被提到
20222022 · 1 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2202.05826 · cs.LG

End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-02-14 · 最近 2025-10-08
2不同的人
2活跃月份
2讨论串
3被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Machine learning systems perform well on pattern matching tasks, but their ability to perform algorithmic or logical reasoning is not well understood. One important reasoning capability is algorithmic extrapolation, in which models trained only on small/simple reasoning problems can synthesize complex strategies for large/complex problems at test time. Algorithmic extrapolation can be achieved through recurrent systems, which can be iterated many times to solve difficult reasoning problems. We observe that this approach fails to scale to highly complex problems because behavior degenerates when many iterations are applied -- an issue we refer to as "overthinking." We propose a recall architecture that keeps an explicit copy of the problem instance in memory so that it cannot be forgotten. We also employ a progressive training routine that prevents the model from learning behaviors that are specific to iteration number and instead pushes it to learn behaviors that can be repeated indefinitely. These innovations prevent the overthinking problem, and enable recurrent systems to solve extremely hard extrapolation tasks.

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atrudeau · 2025-10

“Very cool to see the effectiveness of recurrence on ARC. For those interested in recurrence, here are other works that leverage a similar approach for other types of problems: Language modeling: Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach https://arxiv.org/pdf/2502.05171 Puzzle solving: A Simple Loss Function for Con…”

Less is more: Recursive reasoning with tiny networks原评论 ↗
被提交为 story · 1 次