---
format: "aidr-story-markdown/v1"
id: "490658c4bbf8c0e36f14c612de1570f613d0f4c00c8488eed57150926aa2bd0b"
canonical_url: "https://aidr.today/490658c4?lang=en"
title: "Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-21T00:00:00.000Z"
category: "Agents"
topics: ["agent"]
source_urls: ["https://huggingface.co/papers/2610.28578"]
summary: "Researchers introduced Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to improve long-horizon problem solving through agentic orchestration, verification, and open scientific discovery."
---

# Sage\-A1\.5: From Long\-Horizon Execution to Scientific Exploration with Capability Composition

> [Open the canonical story](<https://aidr.today/490658c4?lang=en>)

**Published:** 2026-10-21T00:00:00.000Z
**Category:** Agents
**Topics:** agent

## Summary

Researchers introduced Sage\-A1\.5, a 35B Mixture\-of\-Experts agentic model that builds on A1 to improve long\-horizon problem solving through agentic orchestration, verification, and open scientific discovery\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.28578>)