Autonomous Science Network

Interconnected autonomous labs for accelerated discovery

We are building the AISLE ecosystem where AI agents, robotics, and leadership-class HPC co-orchestrate experiments across institutions. The result is a continuously learning, interoperable laboratory fabric that compresses discovery cycles from years to weeks.

Agentic orchestrationClosed-loop planning and decisioning
Data fabricFAIR provenance and federated access
Trust and verificationAuditable claims, validated against reality
Upcoming event

A2SD-2026 Workshop

2nd Advancing Autonomous Scientific Discovery Workshop — co-located with ISC High Performance 2026.

A2SD-2026 banner
  • When: June 26, 2026 · 2:00pm–6:00pm CEST
  • Where: Hamburg, Germany · Hall 10, 1st Floor
View workshop details

AISLE network architecture

The AISLE architecture defines how autonomous labs exchange data, reasoning, and experiments across institutions. It unifies instrumentation, intelligent data management, and agentic decisioning through a shared data fabric.

  • Instrument integration
    Standardized interfaces that let agents control heterogeneous lab assets.
  • AI decision loops
    Models and agents that adapt experiments based on live observations.
  • Interoperable protocols
    Secure, cross-lab communication for coordinated workflows.
AISLE network overview

Seven dimensions of autonomous science

Our 2026 roadmap organizes the community agenda around seven dimensions — the five we have tracked since AISLE began, plus trust and safety, elevated to first-class concerns because the past year showed them to be prerequisites rather than refinements.

Instrument and cyberinfrastructure integration

Vendor-neutral access to self-driving laboratories, with AI inference moving onto the instruments themselves.

Agent-driven data management

Provenance and quality enforced at the point of capture, where scarce data are made AI-ready by construction.

Agent-driven orchestration

Reasoning agents that plan and coordinate specialized scientific methods, and explain why a result holds.

Interoperable agent interfaces

The consolidating MCP and A2A stack, now joined by an emerging skills layer.

Education and workforce development

The judgment to resist the homogenizing pull of automation.

Trust, verification, and reproducibility

Verification and validation across the lifecycle as a first-class requirement.

Safety, security, integrity, and governance

Screening and accountability where digital design meets physical execution.

The two-year roadmap

Seven dimensions, eighteen milestones, and a scorecard of what the community has actually achieved.

Read the roadmap

Programs and community

We convene workshops, publish reports, and share open roadmaps to align the community around shared technical standards, infrastructure, and governance.

Workshops

Deep technical exchanges on agentic labs, AI workflows, and infrastructure.

View upcoming workshops

BoF Sessions

Open forums to surface requirements and accelerate collaboration.

Browse Birds of a Feather

Reports

Community-authored documents that capture progress and open challenges.

See community reports

Steering Council

Cross-institution leadership guiding strategy and interoperability priorities.

Meet the council

Build the autonomous science fabric with us

Join laboratories, HPC centers, and AI teams working to scale autonomous discovery across scientific domains.