Neuro-Symbolic Agentic Framework Boosts Reasoning in Small Language Models via Knowledge Graph Grounding

Jul 17, 2026

A new study introduces a neuro-symbolic agentic framework designed to enhance the reasoning abilities of small language models (SLMs) such as Gemma 3 and Llama 3.2 by grounding their outputs in knowledge graphs. The approach leverages tool calls for fact extraction and expert hints from a relational graph convolutional network, resulting in 1.5-2x performance improvements on the CLUTRR kinship reasoning benchmark. The research also highlights key challenges, including errors in fact extraction and a distraction effect from noisy, self-generated facts.

Why it matters: This work offers a promising strategy to improve SLM reasoning efficiency without relying on large, resource-intensive models, while also identifying critical limitations in current neuro-symbolic systems.

Full story at: arXiv AI/ML ↗