Iris-mini and Iris-pro are the strongest open-weight search agents in their class

The AllSpark team released Iris-mini and Iris-pro, two open-source search agents built on Qwen models that lead benchmarks among open-weight models in their size classes, according to the accompanying paper. The training data and models also improved performance on tasks they were never trained for, including general tool use and office work.

Iris-mini and Iris-pro are the strongest open-weight search agents in their class The Decoder https://the-decoder.com The AllSpark team has released Iris-mini and Iris-pro, two open-source search agents built on Qwen models that lead benchmarks among open- weight /glossary/weight models in their size classes. According to the paper, the training /glossary/training data and models also improved performance on tasks they were never trained for, including general tool use /glossary/tool-use and office work. The article Iris-mini and Iris-pro are the strongest open-weight search agents in their class https://the-decoder.com/iris-mini-and-iris-pro-are-the-strongest-open-weight-search-agents-in-their-class/ appeared first on The Decoder https://the-decoder.com . Get AI news in your inbox Daily digest of what matters in AI. Key Terms Explained Decoder /glossary/decoder The part of a neural network that generates output from an internal representation. Tool Use /glossary/tool-use The ability of AI models to interact with external tools and systems — browsing the web, running code, querying APIs, reading files. Training /glossary/training The process of teaching an AI model by exposing it to data and adjusting its parameters to minimize errors. Weight /glossary/weight A numerical value in a neural network that determines the strength of the connection between neurons.