LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks

2025-07-07

AI Summary

Dynamic symbolic execution (DSE) in distributed AI systems suffers from poor scalability, low efficiency, and limited capability to detect deep errors induced by complex network communication. Method: This paper proposes LIFT, the first framework to integrate large language models (LLMs) into semantics-preserving, context-sensitive intermediate representation (IR) functional equivalence transformations. LIFT employs a two-stage, semantically verifiable IR optimization pipeline to automatically enhance DSE’s analysis efficiency and generality. Results: Evaluated on real-world binaries, LIFT reduces bigtest execution time by 53.5% and random execution time by 10.24%, while significantly decreasing IR statement count, PUT instruction count, and temporary variable usage. This work establishes the first LLM-driven, formally verifiable IR optimization technique, introducing a novel paradigm for program analysis in distributed systems.

Technology Category

• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Dynamic Symbolic Execution (DSE) is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI systems, DSE plays a crucial role in identifying hard-to-detect bugs, especially those arising from complex network communication patterns. However, traditional approaches to symbolic execution are often hindered by scalability issues and inefficiencies, particularly in large-scale systems. This paper introduces LIFT (Large-language-model Integrated Functional-equivalent-IR Transformation), a novel framework that leverages Large Language Models (LLMs) to automate the optimization of Intermediate Representations (IRs) in symbolic execution. LIFT addresses the challenges of symbolic execution by providing a scalable, context-sensitive solution for IR transformation. The framework consists of two phases: IR Analysis and Optimization, where LLMs optimize time-intensive IR blocks, and Symbolic Execution and Validation, which includes benchmarking and semantic verification to ensure correctness and generalizability. Experiments on real-world binaries demonstrated significant performance improvements, including a 53.5% reduction in execution time for bigtest and a 10.24% reduction for random, along with reductions in IR statements, PUT instructions, and temporary variables. These results demonstrate that LLMs simplify IRs while maintaining functional correctness, enhancing symbolic execution in distributed AI systems.

Problem

• Optimizing symbolic execution scalability in AI networks
• Automating IR transformation using Large Language Models
• Reducing execution time and IR complexity in DSE

Innovation

• LLMs automate IR optimization in symbolic execution
• Scalable context-sensitive solution for IR transformation
• Reduces execution time and IR statements significantly