PulseAugur
中
实时 06:19:42
English(EN) Iris: Climbing to the Search Frontier

Iris搜索代理在网络基准测试中取得新前沿成果

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了Iris-mini和Iris-pro，这是分别在35B-A3B和397B-A17B规模下训练的两个搜索代理。这些代理是使用一种新颖的数据管道开发的，该管道在网络语料库实体图上构建多跳链，并生成对参考模型具有挑战性的问题。训练过程包括与实时搜索进行强化学习（RL）的交替监督微调（SFT），这种方法称为SFT-RL攀登。在进行上下文管理评估时，Iris-pro在BrowseComp和DeepSearchQA等基准测试中取得了优异的成绩，在同等参数范围内超越了其他开源搜索代理。 AI

影响 这些模型提升了开源搜索代理的能力，可能改进网络导航和信息检索。

排序理由 该项目是一篇详细介绍新AI模型和训练方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Iris搜索代理在网络基准测试中取得新前沿成果

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
Tool
该项目是一篇详细介绍新AI模型和训练方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, 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
4 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 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Ziyuan Liu, Hengqi Liu, Zichuan Wang, Yang Qin, Jiachen Liang, Xu Chu, Shaowei Chen, Yuantao Gu, Mu Chuan ·

    Iris：攀登搜索前沿

    arXiv:2609.04304v1 Announce Type: new Abstract: We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse-constructed from the hyperlink structure of a web c…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Iris：攀登搜索前沿

    Two large-scale search agents are trained via a multi-stage pipeline combining supervised fine-tuning and reinforcement learning against live search, achieving state-of-the-art open-source results on complex web benchmarks through rigorous trajectory filtering and inference-time …

相关实体

相关话题