English(EN) EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning

新的EvoIn框架通过进化和内化增强AI智能体的决策能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了EvoIn，一个结合进化方法和内化的新颖智能体微调框架。该方法首先通过分析智能体执行轨迹来进化新的决策程序，并将其临时集成到智能体的框架中。然后，这些经过验证的程序指导智能体生成改进的推理轨迹，随后重写这些轨迹以消除框架依赖性，并将逻辑表达为模型自身的推理。最后，在重写的轨迹上对模型进行微调，使改进后的决策在推理过程中无需进化框架即可持续存在，从而在各种基准测试中获得显著的性能提升。 AI

影响该框架可能带来更强大、更适应性强的AI智能体，使其在执行新任务时具有更好的泛化能力。

排序理由该集群包含一篇详细介绍新AI研究框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

Shihan Dou

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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新AI研究框架的学术论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shihan Dou, Shaofan Liu, Zhonghang Lu, Jiahang Lin, Shichun Liu, Binghai Wang, Jiajie Jin, Guanting Dong, Tao Gui, Qi Zhang, Xuanjing Huang · 2026-10-28 04:00

EvoIn：连接进化与内部化以进行智能体微调

arXiv:2609.35290v2 Announce Type: replace Abstract: Recent work has explored improving agents by jointly evolving their harnesses and models, but often takes a ''potpourri'' approach that bundles together new tools, new decision-making procedures, and model adaptation to the evol…

本文如何被排名

报道来源 [1]

EvoIn：连接进化与内部化以进行智能体微调

相关话题