Cover Image

Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Rong, Saha, Suman
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can Large Language Models Simulate Symbolic Execution Output Like KLEE?
by: Feng, Rong, et al.
Published: (2025)

Integrating Symbolic Execution with LLMs for Automated Generation of Program Specifications
by: Yang, Fanpeng, et al.
Published: (2025)

Teaching LLMs Program Semantics via Symbolic Execution Traces
by: Bayer, Jonas, et al.
Published: (2026)

Can Large Language Models Solve Path Constraints in Symbolic Execution?
by: Wang, Wenhan, et al.
Published: (2025)

SEPE-SQED: Symbolic Quick Error Detection by Semantically Equivalent Program Execution
by: Li, Yufeng, et al.
Published: (2024)

Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary
by: Xu, Xiangzhe, et al.
Published: (2023)

Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
by: Sakharova, Marina, et al.
Published: (2025)

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery
by: Shafiuzzaman, Md, et al.
Published: (2026)

Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference
by: Le-Cong, Thanh, et al.
Published: (2025)

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
by: Pei, Yunrui, et al.
Published: (2025)

Scaling Symbolic Execution to Large Software Systems
by: Horvath, Gabor, et al.
Published: (2024)

AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs
by: Liu, Jinshi, et al.
Published: (2026)

SEAL: Symbolic Execution with Separation Logic (Competition Contribution)
by: Brablec, Tomáš, et al.
Published: (2026)

Execution-free Program Repair
by: Huang, Li, et al.
Published: (2024)

Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection
by: Gabbireddy, Divyesh, et al.
Published: (2026)

S$^2$F: Principled Hybrid Testing With Fuzzing, Symbolic Execution, and Sampling
by: Wang, Lianjing, et al.
Published: (2026)

Compiling Code LLMs into Lightweight Executables
by: Shi, Jieke, et al.
Published: (2026)

Trustworthy Distributed Certification of Program Execution
by: Wolf, Alex, et al.
Published: (2024)

Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution
by: Yang, Shuo, et al.
Published: (2024)

Can Emulating Semantic Translation Help LLMs with Code Translation? A Study Based on Pseudocode
by: Chen, Songqiang, et al.
Published: (2025)

AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution
by: Mächtle, Felix, et al.
Published: (2025)

Programming Language Confusion: When Code LLMs Can't Keep their Languages Straight
by: Moumoula, Micheline Bénédicte, et al.
Published: (2025)

Logging Like Humans for LLMs: Rethinking Logging via Execution and Runtime Feedback
by: Wang, Xin, et al.
Published: (2026)

Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
by: Haque, Mirazul, et al.
Published: (2025)

Multi-Pass Targeted Dynamic Symbolic Execution
by: Yavuz, Tuba
Published: (2024)

Mokav: Execution-driven Differential Testing with LLMs
by: Etemadi, Khashayar, et al.
Published: (2024)

Accurate and Extensible Symbolic Execution of Binary Code based on Formal ISA Semantics
by: Tempel, Sören, et al.
Published: (2024)

Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
by: Hu, Li, et al.
Published: (2026)

How Robustly do LLMs Understand Execution Semantics?
by: Spiess, Claudio, et al.
Published: (2026)

Efficient Symbolic Execution of Software under Fault Attacks
by: Fang, Yuzhou, et al.
Published: (2025)

Python Symbolic Execution with LLM-powered Code Generation
by: Wang, Wenhan, et al.
Published: (2024)

NumScout: Unveiling Numerical Defects in Smart Contracts using LLM-Pruning Symbolic Execution
by: Chen, Jiachi, et al.
Published: (2025)

Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation
by: Abdullin, Azat, et al.
Published: (2025)

ScratchEval : A Multimodal Evaluation Framework for LLMs in Block-Based Programming
by: Si, Yuan, et al.
Published: (2026)

Systematic API Testing Through Model Checking and Executable Contracts
by: Ribeiro, Ana, et al.
Published: (2026)

Epistemic Ensembles in Semantic and Symbolic Environments (Extended Version with Proofs)
by: Hennicker, Rolf, et al.
Published: (2024)

Keeping Behavioral Programs Alive: Specifying and Executing Liveness Requirements
by: Yaacov, Tom, et al.
Published: (2024)

SpaceTime Programming: Live and Omniscient Exploration of Code and Execution
by: Döderlein, Jean-Baptiste, et al.
Published: (2026)

SseRex: Practical Symbolic Execution of Solana Smart Contracts
by: Cloosters, Tobias, et al.
Published: (2026)

SESR-Eval: Dataset for Evaluating LLMs in the Title-Abstract Screening of Systematic Reviews
by: Huotala, Aleksi, et al.
Published: (2025)