Cover Image

What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Armengol-Estapé, Jordi, Carbonneaux, Quentin, Zhang, Tianjun, Markosyan, Aram H., Seeker, Volker, Cummins, Chris, Kambadur, Melanie, O'Boyle, Michael F. P., Wang, Sida, Synnaeve, Gabriel, Leather, Hugh James
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Programming Languages
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
by: Cummins, Chris, et al.
Published: (2024)

SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
by: Armengol-Estapé, Jordi, et al.
Published: (2023)

Priority Sampling of Large Language Models for Compilers
by: Grubisic, Dejan, et al.
Published: (2024)

Compiler generated feedback for Large Language Models
by: Grubisic, Dejan, et al.
Published: (2024)

Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
by: Cummins, Chris, et al.
Published: (2024)

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
by: Gu, Alex, et al.
Published: (2024)

Forklift: An Extensible Neural Lifter
by: Armengol-Estapé, Jordi, et al.
Published: (2024)

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
by: Gehring, Jonas, et al.
Published: (2024)

Does Culture Matter in Economic Behaviour?
by: Edward O’Boyle
Published: (2016)

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
by: Wei, Yuxiang, et al.
Published: (2025)

Fel's Conjecture on Syzygies of Numerical Semigroups
by: Chen, Evan, et al.
Published: (2026)

Dead ends in square-free digit walks
by: Chen, Evan, et al.
Published: (2026)

Almost all primes are partially regular
by: Chen, Evan, et al.
Published: (2026)

CWM: An Open-Weights LLM for Research on Code Generation with World Models
by: FAIR CodeGen team, et al.
Published: (2025)

ABC implies that Ramanujan's tau function misses almost all primes
by: Angdinata, David Kurniadi, et al.
Published: (2026)

On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
by: Armengol-Estapé, Jordi, et al.
Published: (2024)

LLMs versus the Halting Problem: Characterizing Program Termination Reasoning
by: Sultan, Oren, et al.
Published: (2026)

Absorption and Effects of Patch Test Preparations of Hydroperoxides of Limonene and Hydroperoxides of Linalool in Human Ex Vivo Skin
by: Aoife Clancy, et al.
Published: (2026)

Social Financing Alternatives for Social Economy Enterprises: Coop57
by: Glòria Estapé-Dubreuil
Published: (2014)

Verificación de los Pronósticos de Aeródromo en Cuba (Parte I)
by: Guillermo Armengol Matas
Published: (2022)

El SIDA y la agricultura : una amenaza para los trabajadores rurales y la producción alimentaria / Susan Leather
by: Leather, Susan

Gravitational self-force with hyperboloidal slicing and spectral methods
by: Leather, Benjamin
Published: (2024)

Re-evaluating sample efficiency in de novo molecule generation
by: Thomas, Morgan, et al.
Published: (2022)

SIDA et agriculture: une menace pour les travailleurs ruraux et la production de nourriture
by: Susan Leather (Author)
Published: (2003)

El SIDA y la agricultura: una amenaza para los trabajadores rurales y la producción alimentaria
by: Susan Leather (Author)
Published: (2003)

AIDS and agriculture: a threat to rural workers and food production
by: Susan Leather (Author)
Published: (2003)

Comparable Worth: The Limitations of Federal Legislation and Litigation.
by: Leather, Deborah J.
Published: (1988)

ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations
by: Gu, Alex, et al.
Published: (2025)

Gain understanding of process for entering pipelinewith executive search firms
by: Claudine McCarthy
Published: (2025)

Execution Outcome Attestation for AI Agents and Automated Systems (IETF Internet-Draft draft-morrow-sogomonian-exec-outcome-attest-00)
by: Morrow, et al.
Published: (2026)

Detecting Prefix Bias in LLM-based Reward Models
by: Kumar, Ashwin, et al.
Published: (2025)

Mitigating hemoglobin‐induced nephropathy: ApoHb‐hp protection of podocytes
by: Daniela Lucas, et al.
Published: (2024)

What is not measured cannot be improved: the urgency to understand causes of HIV‐related deaths in Latin America
by: Blanca Lopez‐Villalba, et al.
Published: (2025)

Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
by: Zhang, Ying, et al.
Published: (2026)

I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition
by: Vasilakis, Yannis, et al.
Published: (2024)

‘I cannot accept it’ distressing experiences in parents of children diagnosed with cancer: A qualitative study
by: Xiaohuan Jin, et al.
Published: (2024)

Correction to “What is not measured cannot be improved: the urgency to understand causes of HIV‐related deaths in Latin America”
Published: (2026)

I declare this to be my last will: Teobert Maler's testament and its execution
by: Alma Durán-Merk
Published: (2011)

Chain-of-Description: What I can understand, I can put into words
by: Guo, Jiaxin, et al.
Published: (2025)

Guided Tensor Lifting
by: Li, Yixuan, et al.
Published: (2025)