[Paper] Box Maze: A Process-Control Architecture for Reliable LLM Reasoning

Source: arXiv - 2603.19182v1

Overview

Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under adversarial prompting. Existing safety approaches — such as reinforcement learning from human feedback (RLHF) and output filtering — primarily operate at the behavioral level and may lack explicit architectural mechanisms for enforcing reasoning process integrity. This paper proposes the Box Maze framework, a conceptual process-control architecture that decomposes LLM reasoning into three explicit layers: memory grounding, structured inference, and boundary enforcement. We introduce preliminary simulation-based evaluation involving progressive boundary erosion scenarios across multiple heterogeneous LLM systems (DeepSeek-V3, Doubao, Qwen). Results from n=50 adversarial scenarios suggest that explicit cognitive control layers may improve consistency in boundary maintenance, with architectural constraints reducing boundary failure rates from approximately 40% (baseline RLHF) to below 1% under adversarial conditions. While current validation is simulation-based, these preliminary results indicate that process-level control may offer a promising direction for improving reliability in large language model reasoning.

Key Contributions

This paper presents research in the following areas:

• cs.AI
• cs.CL

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.AI.

Authors

• Zou Qiang

Paper Information

• arXiv ID: 2603.19182v1
• Categories: cs.AI, cs.CL
• Published: March 19, 2026
• PDF: Download PDF