Agent Orchestration and Planning | Paper Reading | Bloss0m

← Back to Paper Reading

Raven Paper Reading: How a Harness of Harnesses Plans Multi-Agent Work

Advanced

Agent Orchestration and Planning: Part 1 , Note: Oct 1, 2026 , Paper: 2026 , AI Systems

Raven composes model–harness pairs as specialists and asks a Host Agent to plan a dependency DAG. This reading unpacks harness composition, the MAOB benchmark, and what its +10.4/+10.5 percentage-point result actually measures: graph planning match, not successful worker execution.

Understand it in 90 seconds

Read the full deep dive

For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.

Speaking & contact