[Paper] Implicit Patterns in LLM-Based Binary Analysis

Source: arXiv - 2603.19138v1

Overview

Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploration over hundreds of reasoning steps remains poorly understood, due to limited context windows and implicit token-level behaviors. We present the first large-scale, trace-level study showing that multi-pass LLM reasoning gives rise to structured, token-level implicit patterns. Analyzing 521 binaries with 99,563 reasoning steps, we identify four dominant patterns: early pruning, path-dependent lock-in, targeted backtracking, and knowledge-guided prioritization that emerge implicitly from reasoning traces. These token-level implicit patterns serve as an abstraction of LLM reasoning: instead of explicit control-flow or predefined heuristics, exploration is organized through implicit decisions regulating path selection, commitment, and revision. Our analysis shows these patterns form a stable, structured system with distinct temporal roles and measurable characteristics. Our results provide the first systematic characterization of LLM-driven binary analysis and a foundation for more reliable analysis systems.

Key Contributions

This paper presents research in the following areas:

• cs.AI
• cs.CR
• cs.SE

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.AI.

Authors

• Qiang Li
• XiangRui Zhang
• Haining Wang

Paper Information

• arXiv ID: 2603.19138v1
• Categories: cs.AI, cs.CR, cs.SE
• Published: March 19, 2026
• PDF: Download PDF