{"slug": "iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent", "title": "Iris-pro scores 92.9 on DeepSearchQA with a single ReAct agent", "summary": "Iris-pro, a 397B parameter search agent developed by an open-source research team, achieved a 92.9 accuracy score on the DeepSearchQA benchmark with context management enabled, setting a new state-of-the-art result for open-source search agents. The agent, along with Iris-mini (35B-A3B), was trained at massive scales and demonstrates improved multi-hop reasoning and retrieval performance, enabling production teams to deploy more reliable search agents without proprietary systems.", "body_md": "[arXiv](https://arxiv.org/abs/2609.04304)\n\n### Iris-pro scores 92.9 on DeepSearchQA with a single ReAct agent\n\nWhich summary reads better? Pick one — models revealed after.Both summaries are AI-generated.\n\nIris-pro, a 397B parameter search agent, achieves 92.9 accuracy on DeepSearchQA with context management enabled, setting a new benchmark for open-source search agents. This pushes the frontier of multi-hop reasoning and retrieval performance, enabling production teams to deploy more reliable and efficient agents for complex search tasks without requiring proprietary systems or costly test-time verification.\n\nTwo search agents, Iris-mini and Iris-pro, were trained at massive scales (35B-A3B and 397B-A17B) and achieved state-of-the-art results among open-source search agents, reaching scores of up to 92.9 on certain benchmarks, which enables shipping more accurate and capable search agents in production environments.", "url": "https://wpnews.pro/news/iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent", "canonical_source": "https://www.snipvote.com/story/cmtqx245h000aqgzjgzaewcjg", "published_at": "2026-09-07 07:56:42.250768+00:00", "updated_at": "2026-09-07 07:56:43.783477+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-agents", "natural-language-processing"], "entities": ["Iris-pro", "Iris-mini", "DeepSearchQA"], "alternates": {"html": "https://wpnews.pro/news/iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent", "markdown": "https://wpnews.pro/news/iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent.md", "text": "https://wpnews.pro/news/iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent.txt", "jsonld": "https://wpnews.pro/news/iris-pro-scores-92-9-on-deepsearchqa-with-a-single-react-agent.jsonld"}}