Skip to content

MetaCodeGAN-MPC: a multi-pattern conditional GAN with differentiable conformance loss for automated test input generation

Aug 2026 · International Conference on Automated Software Engineering · Vol 33 · 0 citations · 46 references

TL;DR

The results show that adversarial learning with explicit structural supervision is a practical route to structured test-input synthesis.

View source

Similar papers

Open access Aug 2026

RL–LLMfuzzer: reinforcement learning–guided dual–model differential fuzzing for compiler testing

RL-LLMfuzzer, a reinforcement learning and LLM-based differential fuzzing framework that has successfully unearthed 28 officially confirmed vulnerabilities in GCC and LLVM/Clang, establishing a highly efficient and scalable paradigm for LLM-driven compiler validation.

Donghui Li, Yingying Li, Bo Zhao et al. · 0 citations
Preprint Aug 2026

CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation

CHORUS is presented, a post-training framework that pushes performance beyond what a conventional supervised fine-tuning (SFT)-to-reinforcement learning (RL) pipeline achieves, and consolidates the resulting specialists into a single 4B model.

Hejia Zhang, Sheng Lu, Zhongming Yu et al. · 0 citations
Open access Jul 2026

Test-Free Fault Localization Through Deep Source Code Analysis Using Encoder-Based Language Models

A refined training strategy is presented, leveraging an encoder-based approach, to address two key challenges in FL: (1) the accurate classification of lines of code according to their suspiciousness scores, and (2) the class imbalance inherent in this type of problem.

Jesus-Angel del-Hoyo-Gabaldon, Antonio Garcia-Cabot, Eva García-López et al. · 0 citations
Open access 2026

Team Poznan at SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios

Detecting machine-generated code is crucial for maintaining software security, quality and academic integrity. Traditional approaches often rely on stylistic or statistical features, which are increasingly circumvented by advanced code generation models. This paper introduces a novel approach leveraging Graph Neural Networks (GNNs) to capture the structural characteristics of code, specifically modeling source snippets as Abstract Syntax Trees (ASTs). To enhance semantic comprehension, we integrate pre-trained CodeBERT embeddings into the architecture, creating a hybrid model that incorporates structural and semantic information. We evaluate our approach on SemEval-2026 Task 13, covering binary detection, multi-class authorship attribution, and hybrid code classification. Experimental results demonstrate that our GNN-based structural analysis outperforms standalone stylistic and transformer-based base-lines across all subtasks, particularly in multi-class and adversarial settings. This work highlights the potential of GNNs for a more structural understanding of code authorship.

Dawid Siera, Anatol Kaczmarek, Wiktor Kamzela et al. · 0 citations
Preprint Aug 2026

Entropy-based Code Adversarial Translation for Real-world Repository Migration

This work proposes Entropy-based Code Adversarial Translation (ECAT), a multi-agent framework for automated Android-to-HarmonyOS repository migration and introduces A2H-RepoBench, the first real-world benchmark for Android-to-HarmonyOS repository migration.

Yushun Tang, Yi-Fan Cao, Zhicheng Chen et al. · 0 citations
Preprint Jul 2026

CoGate: Confidence-Gated Co-Decoding for Secure Code Generation

CoGate is proposed, a confidence-gated co-decoding approach that controls the expert's influence on the co-decoding process based on its confidence, and outperforms existing co-decoding methods (CoSec+) across multiple benchmarks.

Minghao Hu, Lannan Luo, Allen G. Roush et al. · 0 citations