Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes

Abstract:This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative AI systems in business processes. Rather than treating LangGraph, a low-level orchestration framework for stateful agents, as a model-quality benchmark target, we present three executable recipes -- SQL analytics with repair loops, agentic retrieval-augmented generation with evidence gating, and human-in-the-loop policy review with interrupt and checkpoint recovery -- to show how typed state, conditional routing, deterministic tools, retries, interrupts, checkpoints, and traces fit together. LangGraph is positioned by workflow-complexity fit, not as a universal default: simpler ReAct-style or plain SDK loops may be better for basic tool use, schema-first tools for structured extraction and validation, and DSPy when prompt or program optimization is the main goal. Each recipe explains when LangGraph is worth the extra structure and which implementation patterns make routes, pauses, and audit trails explicit product behavior rather than hidden prompt logic.

25 pages, 2 figures. With ancillary code

Artificial Intelligence (cs.AI); Software Engineering (cs.SE)

arXiv:2607.19297 [cs.AI]

(or arXiv:2607.19297v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.19297 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

benchmarks/datasets/agentic_rag.json

benchmarks/datasets/hitl_policy_review.json

benchmarks/datasets/sql_analytics.json

data/corpus/documents.json

data/policies/policy_docs.json

prompts/shared.yaml

requirements.lock

src/langgraph_study/__init__.py

src/langgraph_study/common/paths.py

src/langgraph_study/common/sql_tools.py

src/langgraph_study/llm/__init__.py

src/langgraph_study/llm/client.py

src/langgraph_study/llm/config.py

src/langgraph_study/llm/mock_brain.py

src/langgraph_study/llm/tools.py

src/langgraph_study/tracing/__init__.py

src/langgraph_study/tracing/recorder.py

src/langgraph_study/workflows/agentic_rag/graph.py

src/langgraph_study/workflows/agentic_rag/logic.py

src/langgraph_study/workflows/hitl_policy_review/graph.py

src/langgraph_study/workflows/hitl_policy_review/logic.py

src/langgraph_study/workflows/sql_analytics/graph.py

src/langgraph_study/workflows/sql_analytics/logic.py

tests/test_recipes.py

(23 additional files not shown) You must enabled JavaScript to view entire file list.

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.