Agentic Capabilities: A Tutorial Introduction

Deployment patterns from local execution to autonomous systems

We provide here example code that implements a set of agentic capabilities of increasing sophistication, from local execution to governed, autonomous scientific systems.

The code makes use of two complementary agent frameworks:

Why both? Production scientific agents need both capabilities. LangGraph excels at LLM orchestration but runs in a single process. Academy excels at distributed execution but doesn’t handle LLM reasoning. Together, they enable intelligent agents that run anywhere—from laptops to federated DOE infrastructure.

See these slides for a brief review of these two systems, and one more, Microsoft Agent Framework.

There are excellent tutorial materials online for LangGraph and for Academy. Here we focus on showing how to use the two systems, independently and together, to realize scalable agentic systems for science.

Getting Started: Tutorial Review of Agentic Patterns

Building Scientific Agents — Learn to build production scientific agents:

  1. LLM Agents — Build agents that reason and call tools (LangGraph)
  2. Distributed Agents — Run agents across machines (Academy)
  3. Production Agents — Combine both for real deployments
Additional Resources  
LLM Configuration Configure OpenAI, Ollama, or FIRST backends

Code Samples by Area

The sample code shows how to implement a series of increasingly sophisticated agentic patterns.

1. Local Agent Execution

LangGraph, Academy

Your on-ramp to CAF. Run persistent, stateful agents on a laptop or workstation—no federation required.

Status: Mature

2. Federated Agent Execution

LangGraph + Academy

Cross-institutional agent execution under federated identity and policy.

Status: Mature

3. Massively Parallel Agent Inference

LangGraph, Aegis

Fan out thousands of LLM requests in parallel on HPC.

Status: Prototype

4. Governed Tool Use at Scale

Academy governance

Invoke expensive, stateful, or dangerous tools under proactive policy enforcement.

Status: WIP

5. Multi-Agent Coordination

Shared state + policy + budgets

Many agents under shared governance—within one institution or across many.

Status: Emerging

6. Long-Lived Autonomous Agents

Lifecycle management

Agents that persist for days to months, maintaining state, memory, and goals.

Status: Emerging

7. Agent-Mediated Scientific Workflows

Dynamic workflow construction

Agents dynamically construct, adapt, and execute scientific workflows.

Status: Early

Capability stages from Local to Workflows

Maturity Levels

Level Meaning
Mature Documented with working examples on this site
Prototype Demonstrated on DOE systems; documentation in progress
WIP Work in progress
Emerging Active development; early adopters welcome
Early Early stage; design and prototyping

Capability Matrix

Stage Capability What you can do CAF Components Where it runs Scale Status
1 Local Agent Execution Run persistent, stateful agents LangGraph Laptop, workstation, VM Single agent Mature
2 Federated Agent Execution Invoke tools under federated identity LangGraph + Academy DOE HPC Multi-resource Mature
3 Parallel Agent Inference Fan out thousands of LLM requests LangGraph + FIRST HPC accelerators O(10³–10⁴) streams Prototype
4 Governed Tool Use Invoke tools under policy enforcement Academy governance DOE HPC O(10²–10³) tools WIP
5 Multi-Agent Coordination Coordinate agents under shared governance Shared state + policy Distributed O(10²–10³) agents Emerging
6 Long-Lived Agents Persistent agents with memory and goals Lifecycle management Any Days–months Emerging
7 Agent Workflows Dynamic workflow construction Workflow integration DOE infrastructure Varies Early

Scale notation: O(10²) means “order of 100” (tens to hundreds), O(10³) means “order of 1,000” (hundreds to thousands), etc. These indicate typical operating ranges, not hard limits.

Examples Index

All examples support multiple LLM backends (OpenAI, FIRST, Ollama) and include a mock mode for testing without API keys.

Local Agents

Example Tech Description Key Pattern
AgentsCalculator LangGraph Minimal tool-calling agent @tool decorator
AgentsRAG LangGraph Retrieval-augmented generation Vector search
AgentsDatabase LangGraph Natural language data queries Pandas integration
AgentsAPI LangGraph External API calls PubChem REST API
AgentsConversation LangGraph Stateful conversation Short/long-term memory
AgentsLangGraph LangGraph 5-agent pipeline StateGraph orchestration
AgentsAcademyBasic Academy Minimal Academy example Two-agent messaging
AgentsRemoteTools Academy Remote tool invocation Coordinator + ToolProvider
AgentsPersistent Academy Persistent workflows Checkpoint and resume
AgentsFederated Academy Federated collaboration Cross-institutional (DOE labs)
AgentsAcademy Academy 5-agent pipeline Agent-to-agent messaging
AgentsAcademyHubSpoke Academy Hub-and-spoke pattern Central orchestrator
AgentsAcademyDashboard Academy Live progress dashboard Rich TUI
AgentsHybrid Both Academy + LangGraph hybrid Distributed LLM agents

Federated Agents

Example Tech Description Key Pattern
AgentsHPCJob LangGraph HPC job submission Batch scheduler lifecycle
CharacterizeChemicals Academy Molecular properties LLM-planned RDKit + xTB

Governed Tool Use

Example Tech Description Key Pattern
AgentsGovernedTools LangGraph Policy enforcement Budget, rate limits, approval

Multi-Agent Coordination

Example Tech Description Key Pattern
AgentsCoordination LangGraph Shared resources Budget, blackboard, claims

Long-Lived Agents

Example Tech Description Key Pattern
AgentsCheckpoint LangGraph Persistent workflows Checkpoint/resume

Agent Workflows

Example Tech Description Key Pattern
AgentsWorkflow LangGraph Dynamic DAG construction Adaptive execution

Credits

Thanks to Kyle Chard, Yadu Babuji, Ian Foster, Suman Raj, and others for material and feedback.