Skip to content
conftrace_
2026 ICML ICML 2026

TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains

Enhancing Large Reasoning Models (LRMs) for specialized domains remains a critical challenge. While recent industrial frameworks attempt to encapsulate Standard Operating Procedures into modular "skills" for dynamic retrieval, utilizing them via context engineering often proves insufficient for complex workflows, leading to "Cognitive Drift." To mitigate this, we propose $Thought Guidance-Retrieval Augmented Generation (TG-RAG)$, a Retrieval-Augmented framework that effectively steers the generation process without relying solely on the model’s self-correction. Built upon an Expert Procedure Graph (EPG) that formalizes unstructured SOPs, the framework uniquely employs a dynamic $“Interrupt-Retrieve-Generate" (IRG)$ mechanism to actively inject step-specific directives into the model’s reasoning process. Extensive evaluations show that TG-RAG achieves competitive performance, demonstrating advantages in specialized domains by ensuring faithful adherence to domain SOPs. Code is available at https://github.com/V1ncent-S/Thought-Guidance.

More from ICML 2026

All ICML 2026 papers →