English(EN) Marathoner: Ultra-Long-Horizon Autonomous Intelligence

新AI代理Marathoner掌握超长周期任务

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了Marathoner，一个专为超长周期任务执行设计的自主代理模型。该模型利用一个训练后管道，从大型GitHub拉取请求中合成挑战性任务，并将它们链接起来以达到前沿水平的难度。Marathoner采用了一种新颖的奖励策略，即后期奖励（Later Stage Bonus Reward），以鼓励持续努力，并在需要长时间执行和大量工具调用的基准测试中，展示出比基础模型甚至专有模型更优异的性能。 AI

影响这项研究可能使AI代理能够处理以前只有人类才能完成的复杂、长期的项目。

排序理由该集群描述了一篇关于AI模型及其方法的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于AI模型及其方法的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Ruiyang Zhang, Jinpeng Ou, Yifan Xie, Jingang Zhou, Lirui Pan, Qingpei Guo, Zhedong Zheng · 2026-11-05 05:00

马拉松选手：超长视距自主智能

arXiv:2609.34378v2 Announce Type: replace Abstract: Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a specific objective. In this paper, we propose Mara…

本文如何被排名

报道来源 [1]

马拉松选手：超长视距自主智能

相关实体

相关话题