Coral AI LabsCoral Autoresearch
AI agents can propose ideas, test them and improve them. That’s automated research.
We coordinate how they learn together.
Follow a GPU optimisation experiment
The goal: perform the same calculation using fewer GPU cycles.
Explore
Four Claude Code agents work on a faster GPU kernel—the code that tells a GPU how to perform a calculation.
Each agent proposes experiments.
Four agents investigate candidate approaches in parallel.
Test
An experiment produces evidence the agents can use to choose what to try next.
234evaluations per configuration
The budget stays the same in both runs.
Each candidate is evaluated. The measured result returns to its agent.
Compare
We bring the agents together every 16 evaluations to share evidence and agree on different directions.
A shared blackboard becomes a working discussion.
Evidence moves from all four agents into a shared meeting and back to the team.
Improve
Agents return to their experiments with the team’s findings, not just their own.
Separate investigations. Shared learning.
The agents pursue distinct next experiments after exchanging findings.
The result
A faster kernel from the same four agents and the same evaluation budget.
1,159 → 1,097 GPU cycles.
We changed how the agents worked together.
The experiment
The shared-blackboard run reached 1,159 GPU cycles. Adding coordination meetings reached 1,097: 62 fewer cycles, a 5.35% reduction. Lower is better.
Automated research is a method, not a single field. It applies to problems where agents can propose candidates and measure them against a defined objective. This experiment optimised a GPU kernel.
Our September 2026 research summary
Our next research direction
We’re developing shared research trees so agents can pursue separate ideas, review results and build on successful work. Scheduled meetings remain our strongest tested configuration.
