Shanghai AI Laboratory releases Sage-A1.5 for scientific agents

Oct 22, 2026
Sage-A1.5 is a 35 billion parameter mixture of experts model that supports parallel subagents, task verification, tool use and long context scientific work.

Shanghai Artificial Intelligence Laboratory released Sage-A1.5, a 35 billion parameter mixture of experts model for scientific and agentic tasks, as detailed in its Hugging Face model card. The open weight model is available under the Apache 2.0 license and natively supports a 256K token context window.

Agentic orchestration lets Sage-A1.5 divide tasks among parallel subagents with separate contexts. An optional verification mode allows the model to review progress, validate evidence and change its approach during a task. It also supports function calling and tools such as APIs, code interpreters and search engines.

The lab reports scores of 92.0 on XBench-DS-2510, 95.1 on GAIA and 61.2 on SWE-bench Pro. Developers can serve the model with SGLang or vLLM, while YaRN configuration can extend its context window to 512K tokens.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.