PulseAugur
中
实时 11:14:42
English(EN) LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization

新框架LongSearchEval评估LLM网络搜索能力

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出LongSearchEval，一个旨在评估大型语言模型（LLM）长视距网络搜索能力的新框架。该框架利用轨迹感知代理协议来收集和分析真实的交互轨迹，与现有方法相比，能够进行更准确的行为评估和细粒度的错误定位。LongSearchEval被用于在100个任务上评估八个家族的16个模型，产生了1,600个保留运行和超过6,500个自动标记的故障节点，人类验证证实了标签和特征对应性的一致性很高。 AI

影响 该框架可能带来更强大的LLM评估，推动代理式网络搜索能力的改进。

排序理由 该条目描述了一篇介绍LLM新评估框架的学术论文。[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 →

新框架LongSearchEval评估LLM网络搜索能力

本文如何被排名

Signal score
10 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该条目描述了一篇介绍LLM新评估框架的学术论文。[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, product
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]

  1. arXiv cs.AI TIER_1 English(EN) · Jialiang Liu, Shusheng Li, Wenjun Tan ·

    LongSearchEval：通过具有故障节点定位的轨迹感知代理框架评估大型语言模型在长视距网络搜索方面的能力

    arXiv:2610.35150v1 Announce Type: new Abstract: Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring final answer q…

相关实体

相关话题