PulseAugur
EN
LIVE 10:29:33

AllSpark Research unveils Iris, an open-weight web search agent

By PulseAugur Editorial · [1 sources] ·

AllSpark Research has introduced Iris, an open-weight web search agent system designed to tackle complex, multi-hop questions that often stump current language models. Iris utilizes two models, Iris-mini and Iris-pro, post-trained from the Qwen3.5/3.6 MoE series, and achieves state-of-the-art results on benchmarks like BrowseComp and Humanity's Last Exam. The system's innovation lies in its training methodology, SFT-RL climbing, which alternates between supervised fine-tuning and reinforcement learning, and its focus on an execution harness to manage context saturation during long-horizon searches. AI

IMPACT Iris's novel training approach and performance on complex search tasks could advance the capabilities of open-weight agents for intricate information retrieval.

RANK_REASON The cluster describes the release of a new open-weight agent system, Iris, with novel training methods and benchmark performance. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AllSpark Research unveils Iris, an open-weight web search agent

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
Significant
The cluster describes the release of a new open-weight agent system, Iris, with novel training methods and benchmark performance. [lever_c_demoted from frontier_release: 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
model release, 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
3 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 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Prabhakar Chaudhary ·

    Iris: How SFT-RL Climbing Trains Open-Weight Agents to Search the Web Like a Researcher

    <h1> Iris: How SFT-RL Climbing Trains Open-Weight Agents to Search the Web Like a Researcher </h1> <p>Web search sounds simple until you try to automate it for hard questions. Ask a language model to find the founding date of a company, and it will usually succeed. Ask it to trac…

RELATED ENTITIES

RELATED TOPICS