PulseAugur
中
实时 08:31:56
English(EN) KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

KV-PRM论文提出高效的多智能体LLM奖励建模方法

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员提出了一种名为KV-PRM的新方法，用于提高多智能体系统中使用的过程奖励模型（PRM）的效率。与现有的重新编码整个轨迹的基于文本的PRM不同，KV-PRM直接利用LLM推理过程中生成的KV缓存。这种方法将计算成本从O(L^2)显著降低到O(L)，使其更适合长上下文场景。在MATH、GSM8K和AIME等基准测试上的实证结果表明，KV-PRM在性能上能媲美或超越文本-PRM，同时在FLOPs、延迟和内存占用方面提供了显著的降低。 AI

影响 这项研究可以显著提高基于LLM的多智能体系统的可扩展性和效率，从而能够执行更复杂、更长时间的任务。

排序理由 该集群包含一篇详细介绍提高LLM效率新方法的论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

KV-PRM论文提出高效的多智能体LLM奖励建模方法

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
该集群包含一篇详细介绍提高LLM效率新方法的论文。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
53 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 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Dong Bok Lee, Seanie Lee, Sangwoo Park, Minki Kang, Jinheon Baek, Dongki Kim, Dominik Wagner, Jiongdao Jin, Heejun Lee, Tobias Bocklet, Jinyu Wang, Jingjing Fu, Sung Ju Hwang, Jiang Bian, Lei Song ·

    重新思考多领域测试时域缩放的奖励模型

    arXiv:2510.00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic. Prior work has studied both …

  2. arXiv cs.AI TIER_1 English(EN) · Peng Kuang, Haibo Jin, Xiaoyu Han, Yanli Wang, Xiaopeng Yuan, Ye Yu, Kaidi Xu, Haohan Wang ·

    KV-PRM：通过KV缓存迁移实现高效过程奖励建模以进行多智能体测试时间扩展

    arXiv:2607.09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: the…

  3. arXiv cs.AI TIER_1 English(EN) · Haohan Wang ·

    KV-PRM：通过KV缓存迁移实现高效过程奖励建模，用于多智能体测试时扩展

    Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scra…

相关实体

相关话题