Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Okay how are Add nodes created? Does an LLM come up with the name, guidance and edges for each node or is it a bespoke transformer model?

No idea what this site is. Paper is here: https://arxiv.org/abs/2609.09153

The distinction between a procedural graph and a static workflow seems important: self-editing topology can capture reusable strategy, but it also makes regressions harder to localize. I’d be curious whether the refinement loop treats a successful trajectory as sufficient evidence, or uses counterexamples and held-out tasks to avoid encoding a brittle shortcut. A practical evaluation might report graph churn and rollback frequency alongside task success, since a graph that keeps growing could be trading inference cost and auditability for a small gain. The explicit entity–relation–procedure representation also seems like a promising place to attach permissions or provenance to tool calls.