PulseAugur
中
实时 14:06:45
English(EN) Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling

新的ArchOR代理增强了LLM在优化任务中的可靠性

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了ArchOR，一种旨在提高大型语言模型（LLM）在优化任务中可靠性的新型技能代理。ArchOR通过引入两个新颖的检索模块：Centroid-Aware Representation Learning (CARL) 和 Signature-Guided Retrieval (S3RL)，解决了叙述重写和实例级经验存储的脆弱性问题。CARL优化技能表示排序，而S3RL使用结构签名和加权Jaccard重叠进行候选优先级排序。使用DeepSeek-V4.1-Flash骨干进行测试，ArchOR在五个基准测试中实现了65.00%的Micro-Avg. Pass@1，优于其前身OptSkills。 AI

影响 增强了LLM在结构化问题解决和优化方面的能力，可能提高代理的可靠性。

排序理由 该集群包含一篇详细介绍新方法及其性能评估的学术论文。[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 →

新的ArchOR代理增强了LLM在优化任务中的可靠性

本文如何被排名

Signal score
1 / 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方法及其性能评估的学术论文。[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
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Anran Liu, Benzhao Hou, Zongsheng Cao, Daichao Wang, Lang Chen, Shitong Chen ·

    Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling

    arXiv:2610.41909v1 Announce Type: new Abstract: Large Language Models (LLMs) can turn natural-language optimization tasks into solver-checked answers, but current agents remain brittle under narrative rewrites and often store reusable experience at the instance level. We introduc…

相关实体

相关话题