Webinar: Reasoning Graphs - Self-Learning Deterministic RAG

​Reasoning Graphs: Self-Learning Deterministic RAG

Language model agents reason from scratch on every query, then discard everything they learned. Same question, different answer, no improvement over time.

Reasoning graphs change this by persisting each chain of thought as structured edges tied to the evidence items they evaluated. On the next run, the system surfaces how each piece of evidence has been judged before, giving the model a memory that compounds with use. A companion retrieval graph tightens candidate selection over successive runs, and together both structures form a self-learning feedback loop. No retraining required.

In this session, Matthew Penaroza walks through the architecture, the results (half the errors, 11-point accuracy gain on hard questions, perfect consistency, 47% lower cost, 46% lower latency), and how to apply reasoning graphs to your own RAG pipelines.

Based on the paper: https://arxiv.org/abs/2604.07595

​Speaker

​Matthew Penaroza
(Head of AI Solution Architecture, SurrealDB)

​​Matthew Penaroza is Head of Solution Architecture at SurrealDB, where he helps design and scale distributed AI systems for global enterprises. As the solutions architect behind the core database systems at companies such as Plaid, Uber, and Atlassian, he brings firsthand insight into how the world’s largest organizations design data infrastructure and how those same architectural principles can be applied to AI systems that demand context precision and intelligent data management.

​Joining the webinar

​Once you register, you'll get an email from SurrealDB with your personal join link. Hold onto it - that's your ticket in.