PulseAugur
中
实时 08:14:35
English(EN) Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees

新的LLM路由方法解决成本、安全和评估问题 · 跟踪4个来源

作者 PulseAugur 编辑部 · [5 个来源] ·

研究人员正在开发新的方法来优化大型语言模型（LLM）路由，旨在平衡推理成本与用户满意度和服務水平協議（SLA）。SLARouter是一种在线算法，通过稀疏的用户反馈进行学习，以实现成本最优和SLA合规性，将成本降低高达2.2倍。此外，RouteJudge提供了一个开放平台来评估LLM路由系统，专注于路由器级别的决策质量，并提供了一个用于开发和比较路由算法的工具箱。另外，一种名为强制延迟攻击（FDA）的新攻击被识别出来，它通过强制查询更昂贵的模型来操纵多模态LLM级联，凸显了一个新的安全漏洞。 AI

影响 新的路由策略和安全分析可能对LLM的运行效率和鲁棒性产生重大影响。

排序理由 该集群包含多篇研究论文，详细介绍了LLM路由和安全的新算法和框架。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

新的LLM路由方法解决成本、安全和评估问题 · 跟踪4个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含多篇研究论文，详细介绍了LLM路由和安全的新算法和框架。
Source corroboration
5 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
infra, product, safety
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
75 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [5]

  1. arXiv cs.AI TIER_1 English(EN) · Herbert Woisetschl\"ager, Arastun Mammadli, Ryan Zhang, Shiqiang Wang ·

    具有用户满意度保证的有限用户反馈下的成本最优 LLM 路由

    arXiv:2606.19376v1 Announce Type: cross Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in…

  2. arXiv cs.LG TIER_1 English(EN) · Guannan Lai, Haoran Hu, Han-Jia Ye ·

    RouteJudge：一个用于可复现和偏好感知的大模型路由的开放平台

    arXiv:2606.18774v1 Announce Type: new Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.cn. Different from model-level response evaluation, RouteJudge focuses on rout…

  3. arXiv cs.AI TIER_1 English(EN) · Zhongye Liu, Yaopei Zeng, Yurui Chang, Lu Lin ·

    强制推迟：操纵多模态大语言模型级联中的路由决策

    arXiv:2606.15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper m…

  4. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Shiqiang Wang ·

    在用户满意度保证下，利用有限用户反馈实现成本最优的LLM路由

    Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a funda…

  5. dev.to — LLM tag TIER_1 English(EN) · Nazar Boyko ·

    大语言模型网关：路由、回退和语义缓存

    <p>Here's a line of code that's quietly running in production at a surprising number of companies:<br /> </p> <div class="highlight js-code-highlight"> <pre class="highlight typescript"><code><span class="kd">const</span> <span class="nx">response</span> <span class="o">=</span> …

相关实体

相关话题