English(EN) Code-to-Harness: Distilling Black-Box Optimizers from Self-Play

语言模型通过实践学习搜索策略，可文本化迁移

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员开发了一种名为Code-to-Harness的方法，使语言模型能够通过实践学习数值搜索策略，然后将这些策略提炼成文本。该方法显著降低了黑盒优化任务中的遗憾，其表现优于未受辅助的语言模型，并可与经典优化器相媲美。提炼出的文本策略可跨不同模型迁移，包括Gemini Flash和Claude Sonnet，并在真实世界的生产基准测试中显示出有效性。 AI

影响该方法有望为AI代理在各种应用中的优化策略提供更高效、更具适应性的解决方案。

排序理由该集群包含一篇详细介绍新颖语言模型训练方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 34 / 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颖语言模型训练方法的学术论文。[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: 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.LG TIER_1 English(EN) · Yi Wu, Zheng Ren, Zhiyu Hu, Haochen Wang, Daryl Chang, Li Wei, Ting Wang, Zhen Li, Pooja Gupta, Nitin Jindal, Lukasz Heldt · 2026-09-14 04:00

Code-to-Harness：从自我博弈中提炼黑盒优化器

arXiv:2609.09468v2 Announce Type: replace Abstract: Can an agent learn a numerical search strategy through executable practice and then transfer that strategy as text? We study low-budget black-box optimization, where unaided language models remain well below strong classical opt…

本文如何被排名

报道来源 [1]

Code-to-Harness：从自我博弈中提炼黑盒优化器

相关实体

相关话题