English(EN) Inheritance as an Admission Test for LLM Prompt Merge Operators

新的LLM提示合并测试使用继承而非固定验证器

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种新颖的LLM提示合并算子入学测试，侧重于继承而非固定验证器。该测试根据当前种群评估代理，只有当其最终平均性能超过零代最佳成员时，运行才被视为训练。如果子代理在零剂量基线之上朝着捐赠者的性能移动，并且此移动的置信界达到所请求剂量的二分之一，则允许合并。该研究在谈判任务上使用了Gemini 3.1 Flash-Lite进行评估，发现“append”和“template append”等策略被接受，而“free rewrite”因进展不足而被拒绝。 AI

影响引入了一种新的LLM代理改进评估指标，可能导致更高效的开发。

排序理由关于LLM提示合并新方法的学术论文。[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: 5 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM提示合并新方法的学术论文。[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: 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) · Zan-Kai Chong, Hiroyuki Ohsaki, Bryan Ng · 2026-10-23 04:00

Inheritance as an Admission Test for LLM Prompt Merge Operators

arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a frozen…

本文如何被排名

报道来源 [1]

Inheritance as an Admission Test for LLM Prompt Merge Operators

相关实体

相关话题