Cover Image

Guiding LLM-based Loop Invariant Synthesis via Feedback on Local Reasoning Errors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Tianchi, Yan, Zhenyu, Liu, Junhao, Di, Peng, Zhang, Xin
Format:	Preprint
Published:	2026
Subjects:	Programming Languages
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ranking LLM-Generated Loop Invariants for Program Verification
by: Chakraborty, Saikat, et al.
Published: (2023)

Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
by: Liu, Chang, et al.
Published: (2023)

Generating Functions Meet Occupation Measures: Invariant Synthesis for Probabilistic Loops (Extended Version)
by: Haase, Darion, et al.
Published: (2026)

Probabilistic Guarantees for Practical LIA Loop Invariant Automation
by: Kumar, Ashish, et al.
Published: (2024)

A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning
by: King, Daragh, et al.
Published: (2025)

BALI: Branch-Aware Loop Invariant Inference with Large Language Models
by: Wang, Mingxiu, et al.
Published: (2025)

LLM-Guided Compositional Program Synthesis
by: Khan, Ruhma, et al.
Published: (2025)

SpecLoop: An Agentic RTL-to-Specification Framework with Formal Verification Feedback Loop
by: Chang, Fu-Chieh, et al.
Published: (2026)

Loop Invariant Generation: A Hybrid Framework of Reasoning optimised LLMs and SMT Solvers
by: Bharti, Varun, et al.
Published: (2025)

Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models
by: Liu, Ruibang, et al.
Published: (2024)

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
by: Xu, Zhenyu, et al.
Published: (2024)

Algebraic Tools for Computing Polynomial Loop Invariants
by: Bayarmagnai, Erdenebayar, et al.
Published: (2024)

A Denotational Semantics for Quantum Loops
by: Assolini, Nicola, et al.
Published: (2025)

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

Beyond Imprecise Distance Metrics: Trace-Guided Directed Greybox Fuzzing via LLM-Predicted Call Stacks
by: Zhang, Yifan, et al.
Published: (2025)

Error Localization, Certificates, and Hints for Probabilistic Program Verification via Slicing (Extended Version)
by: Schröer, Philipp, et al.
Published: (2025)

Algebraic and Algorithmic Methods for Computing Polynomial Loop Invariants
by: Bayarmagnai, Erdenebayar, et al.
Published: (2024)

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

CIll: CTI-Guided Invariant Generation via LLMs for Model Checking
by: Su, Yuheng, et al.
Published: (2026)

HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
by: Barke, Shraddha, et al.
Published: (2024)

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
by: Khan, M Zafir Sadik, et al.
Published: (2025)

LoopSCC: Towards Summarizing Multi-branch Loops within Determinate Cycles
by: Zhu, Kai, et al.
Published: (2024)

AutoChip: Automating HDL Generation Using LLM Feedback
by: Thakur, Shailja, et al.
Published: (2023)

Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection
by: Liu, Junhao, et al.
Published: (2026)

LLM-Guided Strategy Synthesis for Scalable Equality Saturation
by: Yin, Chenyun, et al.
Published: (2026)

Improving LLM Classification of Logical Errors by Integrating Error Relationship into Prompts
by: Lee, Yanggyu, et al.
Published: (2024)

WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
by: Yu, Haonan, et al.
Published: (2026)

Fully Symbolic Analysis of Loop Locality: Using Imaginary Reuse to Infer Real Performance
by: Zhu, Yifan, et al.
Published: (2026)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
by: Peng, Yun, et al.
Published: (2024)

Error Credits: Resourceful Reasoning about Error Bounds for Higher-Order Probabilistic Programs
by: Aguirre, Alejandro, et al.
Published: (2024)

Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimization
by: Merouani, Massinissa, et al.
Published: (2025)

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
by: Wen, Hongbo, et al.
Published: (2026)

Trace-Guided Synthesis of Effectful Test Generators
by: Zhou, Zhe, et al.
Published: (2026)

Mason: Type- and Name-Guided Program Synthesis
by: Geer, Jasper, et al.
Published: (2026)

Composable Effect Handling for Programming LLM-integrated Scripts
by: Wang, Di
Published: (2025)

LLM-Based Repair of Static Nullability Errors
by: Karimipour, Nima, et al.
Published: (2025)

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
by: Qin, Zhanyue, et al.
Published: (2026)

AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback
by: Gao, Zhitao, et al.
Published: (2026)

Probabilistic Concurrent Reasoning in Outcome Logic: Independence, Conditioning, and Invariants
by: Zilberstein, Noam, et al.
Published: (2024)

Optimising Density Computations in Probabilistic Programs via Automatic Loop Vectorisation
by: Lim, Sangho, et al.
Published: (2025)