Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

TL;DR - Procedural Graphs explicitly represent an LLM agent’s workflows as evolving graphs of procedural steps and relationships. This structure helps agents maintain objectives, order tool use, and improve from successful and failed trajectories.

• At each decision point, the agent localizes its active graph node and receives situational guidance derived from the surrounding subgraph.
• An LLM refiner compares failed and successful trajectories, then proposes edits to graph topology and attributes.
• Edits are accepted when they preserve or improve held-out validation performance; rejected edits are retained to discourage repeated mistakes.
• Across multiple datasets, task types, and LLMs, the method consistently outperformed memory-based baselines and could improve minimal or flawed initial graphs.