相关论文: RAG-Based Fuzzing of Cross-Architecture Compilers

Existing LLM-based compiler fuzzers often produce syntactically or semantically invalid test programs, limiting their effectiveness in exercising compiler optimizations and backend components. We introduce ReFuzzer, a framework for refining…

Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasoning capabilities. We introduce Collab-RAG, a collaborative…

While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic…

Despite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical…

BusyBox, an open-source software bundling over 300 essential Linux commands into a single executable, is ubiquitous in Linux-based embedded devices. Vulnerabilities in BusyBox can have far-reaching consequences, affecting a wide array of…

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluations concentrate primarily on correctness, which may not…

Bugs in operating system kernels can affect billions of devices and users all over the world. As a result, a large body of research has been focused on kernel fuzzing, i.e., automatically generating syscall (system call) sequences to detect…

The Resource Public Key Infrastructure (RPKI) has become essential to secure inter-domain routing. Despite its critical role, RPKI software remains largely untested beyond shallow parsing. Existing fuzzers, like AFL++ or libFuzzer, do not…

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers…

Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due…

The advent of Retrieval-Augmented Generation (RAG) has significantly enhanced the ability of Large Language Models (LLMs) to produce factually accurate and up-to-date responses. However, the performance of a RAG system is not determined by…

Large Language Models (LLMs) are driving a shift towards intent-driven development, where agents build complete software from scratch. However, existing benchmarks fail to assess this 0-to-1 generation capability due to two limitations:…

A fundamental problem in cybersecurity and computer science is determining whether a program is free of bugs and vulnerabilities. Fuzzing, a popular approach to discovering vulnerabilities in programs, has several advantages over…

Ensuring the correctness of compiler optimizations is critical, but existing fuzzers struggle to test optimizations effectively. First, most fuzzers use optimization pipelines (heuristics-based, fixed sequences of passes) as their harness.…

We introduce DafnyCOMP, a benchmark for evaluating large language models (LLMs) on compositional specification generation in Dafny. Unlike prior benchmarks that focus on single-function tasks, DafnyCOMP targets programs composed of multiple…

This paper presents an experience report on the development of Retrieval Augmented Generation (RAG) systems using PDF documents as the primary data source. The RAG architecture combines generative capabilities of Large Language Models…

Compilation errors represent a significant bottleneck in software development productivity. This paper introduces WARP (Web-Augmented Real-time Program Repairer), a novel system that leverages Large Language Models (LLMs) and dynamic…

Despite much recent interest in compiler randomized testing (fuzzing), the practical impact of fuzzer-found compiler bugs on real-world applications has barely been assessed. We present the first quantitative and qualitative study of the…

Fuzz testing (fuzzing) is a well-known method for exposing bugs/vulnerabilities in software systems. Popular fuzzers, such as AFL, use a biased random search over the domain of program inputs, where 100s or 1000s of inputs (test cases) are…

Fuzzing -- whether generating or mutating inputs -- has found many bugs and security vulnerabilities in a wide range of domains. Stateful and highly structured web APIs present significant challenges to traditional fuzzing techniques, as…