CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA

TL;DR

CogRAG+ is a training-free framework that improves professional exam question answering by aligning retrieval and reasoning with human cognition, reducing errors and increasing accuracy.

Contribution

It introduces Reinforced Retrieval and cognition-stratified Constrained Reasoning to enhance retrieval and logical consistency without additional training.

Findings

Achieves 85.8% accuracy on the Registered Dietitian exam with Qwen3-8B.

Reduces unanswered rate from 7.6% to 1.4%.

Outperforms standard RAG methods and general models on professional tasks.

Abstract

Professional domain knowledge underpins human civilization, serving as both the basis for industry entry and the core of complex decision-making and problem-solving. However, existing large language models often suffer from opaque inference processes in which retrieval and reasoning are tightly entangled, causing knowledge gaps and reasoning inconsistencies in professional tasks. To address this, we propose CogRAG+, a training-free framework that decouples and aligns the retrieval-augmented generation pipeline with human cognitive hierarchies. First, we introduce Reinforced Retrieval, a judge-driven dual-path strategy with fact-centric and option-centric paths that strengthens retrieval and mitigates cascading failures caused by missing foundational knowledge. We then develop cognition-stratified Constrained Reasoning, which replaces unconstrained chain-of-thought generation with structured templates to reduce logical inconsistency and generative redundancy. Experiments on two representative models, Qwen3-8B and Llama3.1-8B, show that CogRAG+ consistently outperforms general-purpose models and standard RAG methods on the Registered Dietitian qualification exam. In single-question mode, it raises overall accuracy to 85.8\% for Qwen3-8B and 60.3\% for Llama3.1-8B, with clear gains over vanilla baselines. Constrained Reasoning also reduces the unanswered rate from 7.6\% to 1.4\%. CogRAG+ offers a robust, model-agnostic path toward training-free expert-level performance in specialized domains.