Implicit Patterns in LLM-Based Binary Analysis

• URL: http://arxiv.org/abs/2603.19138v1
• Date: Thu, 19 Mar 2026 16:56:56 GMT
• Title: Implicit Patterns in LLM-Based Binary Analysis
• Abstract summary: We present the first large-scale, trace-level study showing that multi-pass LLM reasoning gives rise to structured, token-level implicit patterns.<n>Our results provide the first systematic characterization of LLM-driven binary analysis and a foundation for more reliable analysis systems.
• Score: 6.612857121548629
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models [73.59878306788815]
  ReasoningLens is an open-source framework designed for the hierarchical visualization and diagnostic auditing of complex reasoning chains.<n> ReasoningLens addresses information necropsy by: (1) structuring traces into interactive hierarchies that separate high-level strategy from low-level execution; and (2) leveraging an agentic auditor for automated error detection and tool-augmented verification.
  arXiv  Detail & Related papers  (2026-06-22T14:28:35Z)
• Feedback-Driven Execution for LLM-Based Binary Analysis [6.612857121548629]
  We present FORGE, a system that rethinks LLM-based analysis as a feedback-driven execution process.<n> FORGE interleaves reasoning and tool interaction through a reasoning-action-observation loop.<n>We evaluate FORGE on 3,457 real-world firmware binaries.
  arXiv  Detail & Related papers  (2026-04-16T15:15:58Z)
• PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation [15.91920027845529]
  PRISM (Probabilistic Reasoning Inspection through Semantic and Implicit Modeling) is a framework and diagnostic tool for jointly analyzing both levels.<n>It uncovers systematic patterns in the reasoning process, showing that failed trajectories are more likely to become trapped in unproductive verification loops.<n> PRISM makes these behaviors observable and analyzable rather than relying solely on final-task accuracy.
  arXiv  Detail & Related papers  (2026-03-24T03:31:53Z)
• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• Learning Structured Reasoning via Tractable Trajectory Control [99.75278337895024]
  Ctrl-R is a framework for learning structured reasoning via tractable trajectory control.<n>We show that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns.
  arXiv  Detail & Related papers  (2026-03-02T09:18:19Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Increasing AI Explainability by LLM Driven Standard Processes [0.0]
  This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes.<n>A layered architecture is presented that separates the reasoning space of the LLM from the explainable process space above it.<n> Empirical evaluations show that the system can reproduce human-level decision logic in decentralized governance, systems analysis, and strategic reasoning contexts.
  arXiv  Detail & Related papers  (2025-11-10T13:16:10Z)
• From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs [33.17712742134723]
  We propose a framework that shifts from implicit exploration to structured reasoning through guideline and refinement.<n>First, we extract structured reasoning patterns from successful trajectories and reflective signals from failures.<n>During inference, the model follows these guidelines step-by-step, with refinement applied after each step to correct errors and stabilize the reasoning process.
  arXiv  Detail & Related papers  (2025-09-08T02:11:49Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM [11.181783720439563]
  Large Language Models (LLMs) display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation.<n>RLMs often demonstrate counterintuitive and unstable behaviors, such as performance degradation under few-shot prompting.<n>We introduce a unified graph-based analytical framework for better modeling the reasoning processes of RLMs.
  arXiv  Detail & Related papers  (2025-05-20T03:54:57Z)
• A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
  Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making.<n>With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems.<n>We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
  arXiv  Detail & Related papers  (2025-04-12T01:27:49Z)
• Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking [2.8972218767527527]
  Large Language Models (LLMs) exhibit impressive reasoning abilities, yet their reliance on structured step-by-step reasoning reveals a critical limitation.<n>This work challenges the assumption that step-by-step reasoning is always optimal and highlights the need for adapting reasoning strategies based on task demands.
  arXiv  Detail & Related papers  (2025-02-18T02:58:37Z)
• LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning [74.0242521818214]
  This paper systematically investigates the comparative dynamics of inductive (System 1) versus abductive/deductive (System 2) inference in large language models (LLMs)<n>We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text)<n>Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems.
  arXiv  Detail & Related papers  (2025-02-16T15:54:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.