(CA) Aspire: Can Models Self-Evolve from Vague Goals?

新的基准测试ASPIRE测试LLM从模糊目标中自我进化的能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员推出了ASPIRE，这是一个新的基准测试，旨在测试大型语言模型（LLM）在给定模糊的自然语言目标而非明确任务时的自我进化能力。与依赖人类定义的目标的现有方法不同，ASPIRE要求代理解释目标、识别学习需求、选择数据和更新方法，并创建自己的评估信号。实验表明，虽然代理可以进行训练和进行模型编辑循环，但模型权重的稳定改进仍然具有挑战性，即使是最好的进化代理也未能超越Qwen-Agent等工程化参考。 AI

影响该基准测试可能会推动对更自主、更适应性强的AI系统的研究，这些系统能够从模糊的指令中学习。

排序理由该集群包含一篇介绍LLM自我进化新基准测试的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍LLM自我进化新基准测试的研究论文。[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.CL TIER_1 (CA) · Yuhao Wu, Jingyuan Zhang, Jiajun Shi, Yuxuan Zhang, Xinping Lei, Junting Zhou, Zexuan Wang, Yuchen Wu, Huan Zhou, Duo Wang, Yinzhu Piao, Yongchang Peng, Yunfeng Shi, Jin Chen, Zuo Wang, Jinkai Liu, Jiaheng Liu, Wenxuan Zhang, Shen Yan, Wenhao Huang, Ge Z… · 2026-09-01 04:00

Aspire：模型能否从模糊目标中自我进化？

arXiv:2608.31111v1 Announce Type: new Abstract: Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether the…

本文如何被排名

报道来源 [1]

Aspire：模型能否从模糊目标中自我进化？

相关实体

相关话题