Feedback-Driven Execution for LLM-Based Binary Analysis

• URL: http://arxiv.org/abs/2604.15136v1
• Date: Thu, 16 Apr 2026 15:15:58 GMT
• Title: Feedback-Driven Execution for LLM-Based Binary Analysis
• Abstract summary: 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.
• Score: 6.612857121548629
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Binary analysis increasingly relies on large language models (LLMs) to perform semantic reasoning over complex program behaviors. However, existing approaches largely adopt a one-pass execution paradigm, where reasoning operates over a fixed program representation constructed by static analysis tools. This formulation limits the ability to adapt exploration based on intermediate results and makes it difficult to sustain long-horizon, multi-path analysis under constrained context. We present FORGE, a system that rethinks LLM-based analysis as a feedback-driven execution process. FORGE interleaves reasoning and tool interaction through a reasoning-action-observation loop, enabling incremental exploration and evidence construction. To address the instability of long-horizon reasoning, we introduce a Dynamic Forest of Agents (FoA), a decomposed execution model that dynamically coordinates parallel exploration while bounding per-agent context. We evaluate FORGE on 3,457 real-world firmware binaries. FORGE identifies 1,274 vulnerabilities across 591 unique binaries, achieving 72.3% precision while covering a broader range of vulnerability types than prior approaches. These results demonstrate that structuring LLM-based analysis as a decomposed, feedback-driven execution system enables both scalable reasoning and high-quality outcomes in long-horizon tasks.

Related papers

• 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)
• Implicit Patterns in LLM-Based Binary Analysis [6.612857121548629]
  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.
  arXiv  Detail & Related papers  (2026-03-19T16:56:56Z)
• Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
  We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:28:07Z)
• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents [68.85365034738534]
  We introduce a unified framework for developing tool-augmented geospatial agents trained on satellite imagery, natural-language queries, and detailed reasoning traces.<n>The training pipeline relies on supervised fine-tuning over structured reasoning trajectories, aligning the model with verified multistep tool interactions.<n>The accompanying corpus comprises 14,538 training and 1,169 evaluation instances, with more than 100K reasoning steps in the training split and over 7K reasoning steps in the evaluation split.
  arXiv  Detail & Related papers  (2026-02-19T18:59:54Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• AI Founding Fathers: A Case Study of GIS Search in Multi-Agent Pipelines [0.0]
  Large Language Models (LLMs) show exceptional fluency, but efforts persist to extract stronger reasoning capabilities from them.<n>This paper advances a systematic framework for understanding LLM reasoning and optimization.
  arXiv  Detail & Related papers  (2025-11-12T05:52:55Z)
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution [48.7788770680643]
  Flash-Searcher is a novel parallel agent reasoning framework.<n>It decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths.<n>It achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks.
  arXiv  Detail & Related papers  (2025-09-29T17:39:30Z)
• 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)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation [5.903105418868711]
  We introduce textbfQuARC (Quantity, Analysis, Relative positioning, Collision), a new benchmark based on a food preparation scenario.<n>We tackle two major limitations of current MLLMs: cross-modal distraction and geometric infeasibility.<n>Our method achieves a 76.7% success rate on the benchmark, significantly outperforming the ViLa baseline.
  arXiv  Detail & Related papers  (2025-03-17T11:01:02Z)
• Semantic-Enhanced Indirect Call Analysis with Large Language Models [14.517268546437917]
  This paper proposes Semantic-Enhanced Analysis (SEA) to enhance the effectiveness of indirect call analysis. For common programming practices, indirect calls often exhibit semantic similarity with their invoked targets. SEA generates natural language summaries of both indirect calls and target functions from multiple perspectives.
  arXiv  Detail & Related papers  (2024-08-08T10:04:50Z)

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.