Cover Image

Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Maveli, Nickil, Vergari, Antonio, Cohen, Shay B.
Format:	Preprint
Published:	2026
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

What can Large Language Models Capture about Code Functional Equivalence?
by: Maveli, Nickil, et al.
Published: (2024)

What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces
by: Armengol-Estapé, Jordi, et al.
Published: (2025)

LILO: Learning Interpretable Libraries by Compressing and Documenting Code
by: Grand, Gabriel, et al.
Published: (2023)

Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
by: Cassano, Federico, et al.
Published: (2023)

Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!
by: Fang, Xiangxin, et al.
Published: (2024)

Logically Consistent Language Models via Neuro-Symbolic Integration
by: Calanzone, Diego, et al.
Published: (2024)

Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification
by: Barone, Antonio Valerio Miceli, et al.
Published: (2026)

SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
by: S, Santhosh G, et al.
Published: (2025)

Chain of Execution Supervision Promotes General Reasoning in Large Language Models
by: Chen, Nuo, et al.
Published: (2025)

EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
by: Li, Zhening, et al.
Published: (2025)

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
by: Neo, Clement, et al.
Published: (2024)

BaxBench: Can LLMs Generate Correct and Secure Backends?
by: Vero, Mark, et al.
Published: (2025)

Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
by: Hooda, Ashish, et al.
Published: (2024)

Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
by: Miceli-Barone, Antonio Valerio, et al.
Published: (2026)

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis
by: Wei, Anjiang, et al.
Published: (2025)

$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
by: Zhang, Dylan, et al.
Published: (2024)

Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs
by: Dai, Hankun, et al.
Published: (2025)

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
by: Zhao, Zheng, et al.
Published: (2025)

Evaluating LLMs for Hardware Design and Test
by: Blocklove, Jason, et al.
Published: (2024)

Curriculum Learning for Small Code Language Models
by: Naïr, Marwa, et al.
Published: (2024)

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
by: Wang, Yiting, et al.
Published: (2025)

From Reasoning to Code: GRPO Optimization for Underrepresented Languages
by: Pennino, Federico, et al.
Published: (2025)

Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon
by: Cohen-Inger, Nurit, et al.
Published: (2025)

Code Simulation Challenges for Large Language Models
by: La Malfa, Emanuele, et al.
Published: (2024)

Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
by: Gajjar, Jugal
Published: (2026)

FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?
by: Ravi, Nikil, et al.
Published: (2026)

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
by: Wei, Anjiang, et al.
Published: (2025)

JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models
by: Cao, Jialun, et al.
Published: (2024)

Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks
by: Shen, Chen, et al.
Published: (2026)

An Evaluation Benchmark for Autoformalization in Lean4
by: Gulati, Aryan, et al.
Published: (2024)

On Faster Marginalization with Squared Circuits via Orthonormalization
by: Loconte, Lorenzo, et al.
Published: (2024)

MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks
by: Kadosh, Tal, et al.
Published: (2023)

Operon: Incremental Construction of Ragged Data via Named Dimensions
by: Moon, Sungbin, et al.
Published: (2025)

Program Semantic Inequivalence Game with Large Language Models
by: Miceli-Barone, Antonio Valerio, et al.
Published: (2025)

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning
by: Yang, Chengcao
Published: (2026)

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
by: Gong, Junfeng, et al.
Published: (2025)

Large Language Models for Code Summarization
by: Szalontai, Balázs, et al.
Published: (2024)

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

Spectral Editing of Activations for Large Language Model Alignment
by: Qiu, Yifu, et al.
Published: (2024)

Assessing Code Understanding in LLMs
by: Laneve, Cosimo, et al.
Published: (2025)