Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
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. 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-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing int...
| Authors | Wenjie Lou, Tianshuo Peng, Shiyang Feng et al. |
|---|---|
| Primary category | cs.AI |
| Published | 20 October 2026 |
| Last updated at source | 20 October 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- InternScience/Sage-A1.5-Q4_K_M-GGUFModel · cited by
- seanmiranda/Sage-A1.5Model · cited by
- mlx-community/Sage-A1.5-OptiQ-4bitModel · cited by
- InternScience/Sage-A1.5-F16-GGUFModel · cited by
- InternScience/Sage-A1.5-Q8_0-GGUFModel · cited by
- InternScience/Sage-A1.5-FP8Model · cited by
Recent changes
- 21 Oct 2026 Description: 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. Compared with A1, Sage-A1.5 learns not only to solve individua → 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. Compared with A1, Sage-A1.5 learns not only to solve individua
- 21 Oct 2026 Topics added cs.AI removed hf-daily-papers, mixture-of-experts, agentic model, agentic orchestration, agentic verification, open scientific discovery
Changes detected by Silytics between refreshes of the source.
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 22 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.