What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Sage-A1.5: Agentic Model for Long-Horizon Problem Solving

A 35B Mixture-of-Experts agentic model that advances long-horizon problem solving through adaptive capability composition, featuring improvements in task orchestration, verification mechanisms, and scientific discovery capabilities.

arxiv.org →

Connections

Related to

Raven: Multi-Agent Ecosystem for Composable AI Intelligence Both focus on multi-agent composability and orchestration - Sage-A1.5 through adaptive capability composition, Raven through composable multi-agent ecosystems
Introducing Beam: Reflection's 501B Open-Weight Model Both are large open-weight frontier models (Sage-A1.5 35B MoE, Beam 501B) advancing agentic and long-horizon reasoning capabilities, representing competing approaches in the open model landscape
Muse Spark Open: 816B Open-Weight AI Model Both are large-scale mixture-of-experts models (Sage-A1.5 at 35B MoE, Muse Spark Open at 816B) targeting advanced reasoning and agentic capabilities
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning Both address scaling agentic inference for complex, long-horizon tasks - Sage-A1.5 through adaptive capability composition and MoE architecture, edf16196 through meta-reasoning before task execution

Supports

Trust in Depth: Giving agents more autonomy without losing control Sage-A1.5's verification mechanisms and task orchestration improvements directly address the trust and autonomy control challenges discussed in giving agents more autonomy without losing control
Coding Agent Continual Learning: Analysis of ARC-AGI-3 Problem Solving Sage-A1.5's long-horizon problem solving and verification mechanisms directly support the kind of continual learning and iterative problem solving analyzed in the ARC-AGI-3 coding agent study

Type:	link
First published:	Thursday, 22 October 2026 at 00:40 UTC
Location:	https://arxiv.org/abs/2610.28578v1
URL:	https://mattwood.fyi/i/cd2e5db7

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections