PulseAugur
EN
LIVE 14:59:30

Iris search agents achieve SOTA open-source results on web benchmarks · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

Researchers have developed two large-scale search agents, Iris-mini and Iris-pro, trained at 35B and 397B parameters respectively. These agents utilize a novel data pipeline and training methodology that combines supervised fine-tuning with reinforcement learning against live search. The models achieved state-of-the-art results among open-source search agents on complex web benchmarks like BrowseComp and DeepSearchQA, particularly when employing advanced context management techniques. AI

IMPACT Sets new SOTA for open-source search agents, potentially influencing future web navigation and information retrieval technologies.

RANK_REASON The cluster describes a research paper detailing new AI models and their performance on benchmarks.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Iris search agents achieve SOTA open-source results on web benchmarks · 2 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes a research paper detailing new AI models and their performance on benchmarks.
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
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [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: Climbing to the Search Frontier

    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: Climbing to the Search Frontier

    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 …

RELATED ENTITIES

RELATED TOPICS