🛰️ Daily AI Frontier
‹ back to 2026-09-09

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Research LLM Agents

Ranking

Overall 86
Content 95
Popularity 66

Observed public metrics from 1 member.

Merged summary

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.

Sources (1)

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

arXiv cs.AI Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan Ö. Arık 2026-09-08 arXiv:2609.09153
Public signals Hugging Face upvotes 41
Providers: Hugging Face · Upvotes 41 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-25 14:22:29.895883 UTC

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.
item →