Cover Image

Teaching LLMs Program Semantics via Symbolic Execution Traces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bayer, Jonas, Zetzsche, Stefan, Bouissou, Olivier, Delmas, Remi, Tautschnig, Michael, Kong, Soonho
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Machine Learning Programming Languages
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ATLAS: Automated Toolkit for Large-Scale Verified Code Synthesis
by: Baksys, Mantas, et al.
Published: (2025)

DafnyPro: LLM-Assisted Automated Verification for Dafny Programs
by: Banerjee, Debangshu, et al.
Published: (2026)

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

Execution-Aware Program Reduction for WebAssembly via Record and Replay
by: Baek, Doehyun, et al.
Published: (2025)

NExT: Teaching Large Language Models to Reason about Code Execution
by: Ni, Ansong, et al.
Published: (2024)

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)

EnvTrace: Simulation-Based Semantic Evaluation of LLM Code via Execution Trace Alignment -- Demonstrated at Synchrotron Beamlines
by: van der Vleuten, Noah, et al.
Published: (2025)

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

Taming the Hydra: Targeted Control-Flow Transformations for Dynamic Symbolic Execution
by: Saumya, Charitha, et al.
Published: (2023)

Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code
by: Bouras, Dimitrios Stamatios, et al.
Published: (2026)

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

Divergent Multi-Version Execution (DME): Canonical Instruction-Trace Fault Detection via Structural Address-Space Decorrelation
by: Yrievich, Petro Baran
Published: (2026)

NESA: Relational Neuro-Symbolic Static Program Analysis
by: Wang, Chengpeng, et al.
Published: (2024)

Validating Traces of Distributed Programs Against TLA+ Specifications
by: Cirstea, Horatiu, et al.
Published: (2024)

Toward Programming Languages for Reasoning: Humans, Symbolic Systems, and AI Agents
by: Marron, Mark
Published: (2024)

Assured Automatic Programming via Large Language Models
by: Mirchev, Martin, et al.
Published: (2024)

K-CIRCT: A Layered, Composable, and Executable Formal Semantics for CIRCT Hardware IRs
by: Zhao, Jianhong, et al.
Published: (2024)

LLMs Lean on Priors, Not Programming Language Semantics
by: Thimmaiah, Aditya, et al.
Published: (2025)

A Tool for Automated Reasoning About Traces Based on Configurable Formal Semantics
by: Erata, Ferhat, et al.
Published: (2024)

Is Programming by Example solved by LLMs?
by: Li, Wen-Ding, et al.
Published: (2024)

Intent-aligned Formal Specification Synthesis via Traceable Refinement
by: Ye, Zhe, et al.
Published: (2026)

KAIJU: An Executive Kernel for Intent-Gated Execution of LLM Agents
by: Guerin, Cormac, et al.
Published: (2026)

Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
by: Silva, André, et al.
Published: (2025)

Enabling Memory Safety of C Programs using LLMs
by: Mohammed, Nausheen, et al.
Published: (2024)

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

Dafny as Verification-Aware Intermediate Language for Code Generation
by: Li, Yue Chen, et al.
Published: (2025)

EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking
by: Wei, Anjiang, et al.
Published: (2025)

DINGO: Constrained Inference for Diffusion LLMs
by: Suresh, Tarun, et al.
Published: (2025)

Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs
by: Wu, Valentina, et al.
Published: (2025)

Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters
by: Mitchell, Jacqueline L., et al.
Published: (2025)

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
by: Ugare, Shubham, et al.
Published: (2024)

Finding Missed Code Size Optimizations in Compilers using LLMs
by: Italiano, Davide, et al.
Published: (2024)

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
by: Yu, Simon, et al.
Published: (2026)

CUTECat: Concolic Execution for Computational Law
by: Goutagny, Pierre, et al.
Published: (2024)

Literate Tracing
by: Sotoudeh, Matthew
Published: (2025)

Symbolic Execution Meets Multi-LLM Orchestration: Detecting Memory Vulnerabilities in Incomplete Rust CVE Snippets
by: Abdelrazek, Zeyad, et al.
Published: (2026)

Quantitative Symbolic Patch Impact Analysis
by: Sarker, Laboni, et al.
Published: (2026)

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

Evaluating Program Semantics Reasoning with Type Inference in System F
by: He, Yifeng, et al.
Published: (2025)