In this report, we introduce Sage-A1. 5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition.
ORIGINAL PAPER
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
WHAT WE KNOW
Compared with A1, Sage-A1. 5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.
WATCH NEXT
Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.
EVIDENCE
What the evidence supports so far
Research signals
agent
reasoning
scaling
What remains unverified
The full methodology, effect size, and limitations still require analyst review.
Company impact remains unverified until a direct economic transmission is established.