English(EN) Dreaming in Code for Curriculum Learning in Open-Ended Worlds

新框架使用LLM为AI代理训练生成代码

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一个名为Dreaming in Code (DiCode)的新框架，以改进AI代理的开放式学习。这个无监督环境设计框架使用大型语言模型为环境生成可执行代码，创建了一个指导代理提高能力的课程。在Craftax基准测试中，DiCode使代理能够获得长时程技能，平均回报比基线方法提高了17%，并在具有挑战性的战斗任务中取得成功。 AI

影响该框架通过提供结构化的课程，可以更有效地在复杂的开放式环境中训练AI代理。

排序理由这是一篇详细介绍新框架及其在基准测试中实证结果的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新框架及其在基准测试中实证结果的研究论文。[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.AI TIER_1 English(EN) · Konstantinos Mitsides, Maxence Faldor, Antoine Cully · 2026-09-15 04:00

在开放式世界中为课程学习进行代码的梦想

arXiv:2602.08194v2 Announce Type: replace-cross Abstract: Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models to programmatically generate diverse enviro…

本文如何被排名

报道来源 [1]

在开放式世界中为课程学习进行代码的梦想

相关实体

相关话题