arXiv AI
Jul 13
Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity
arXiv:2509. 23449v2 Announce Type: replace Abstract: Binary code similarity detection is a core task in reverse engineering.
Pluvio: Assembly Clone Search for Out-of-domain Architectures and Libraries through Transfer Learning and Conditional Variational Information Bottleneck
Related stories
arXiv AI
Aug 6
A Unified Model for Cross-Domain Clone Detection via Model Merging
arXiv:2608. 04215v1 Announce Type: cross Abstract: The growing diversity of code clone types, from syntactic copies to cross-language semantic clones to AI-generated duplicates, has created a fragmentation crisis in clone detection.
arXiv AI
Oct 2
Are AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models
The paper investigates whether code large language models (CodeLLMs) inadvertently reproduce proprietary or sensitive code by evaluating seven state‑of‑the‑art training data detection (TDD) methods on eight CodeLLMs. It introduces CodeSnitch, a benchmark of 9,000 function‑level code samples across three languages, each labeled as included or excluded from training data, and applies mutation strategies based on the Type‑1 to Type‑4 code clone taxonomy to test TDD robustness. The study offers a systematic assessment of current TDD techniques for code and suggests directions for developing more effective detection methods.
arXiv Machine Learning
Sep 16
Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
The paper introduces LWVIC4Code, a non‑contrastive, layer‑wise representation learning method for detecting Type‑IV code clones—semantically equivalent fragments that differ syntactically. It builds on the VICReg framework, adding cross‑layer consistency regularization and depth‑dependent weighting to refine semantic information across transformer layers. Experiments on Python and multi‑language datasets show that LWVIC4Code matches or outperforms contrastive baselines and zero‑shot large language models, generalizing well to Java and C# without requiring negative samples.
arXiv AI
Oct 1
EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses
EngramBench is a new benchmark designed to evaluate skill evolution in autonomous agents by focusing on genuine capability abstraction rather than solution copying. It includes 30 learning tasks and 13 unseen transfer tasks that require agents to manage complex, multi-hour development cycles with LLM‑simulated users. The study shows that while static skill banks cannot eliminate the need for precise code implementation, they effectively reduce redundant context and cut overall coding time by more than 55%.
arXiv AI
Jun 3
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
arXiv:2606. 03657v1 Announce Type: new Abstract: Large language models for code generation often need to use APIs that are absent from their pretraining data.
arXiv Computation and Language
Oct 16
Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code Completion
The paper introduces SaraCoder, a retrieval‑augmented framework that improves knowledge density for repository‑level code completion by pruning redundant context and selectively injecting cross‑file dependency definitions within a fixed token budget. It employs a Hierarchical Feature Optimization module to reduce an over‑complete candidate pool in four stages, freeing tokens for an External‑Aware Identifier Disambiguator. Experiments on CrossCodeEval and RepoEval‑Updated demonstrate that SaraCoder outperforms strong RAG baselines such as GraphCoder and Repocoder across multiple code LLMs without increasing token usage, and achieves synergistic gains when combined with other cross‑file methods.
arXiv AI
Oct 15
Simple Baselines are Competitive with Code Evolution
arXiv:2602.16805v2 Announce Type: replace Abstract: Code evolution is a family of techniques that rely on large language models to search through possible computer programs by evolving existing code....
arXiv AI
Aug 25
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
arXiv:2608.22638v1 Announce Type: cross Abstract: Copying a function from a chat window into an editor takes less than a second. For many uses of AI coding tools, that speed is the point; in settings...
arXiv AI
Oct 7
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, e...
arXiv Machine Learning
Aug 4
Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context
arXiv:2608. 02084v1 Announce Type: cross Abstract: Binary function embedding models are trained to encode the semantics of binary code in such a way that they can be generalized to a variety of reverse engineering tasks, such as binary code search, vulnerability detection, or malware classification.
arXiv AI
Aug 13
Program Semantic Inequivalence Game with Large Language Models
arXiv:2505. 03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.