Related papers: SieveFL: Hierarchical Runtime-Aware Pruning for Sc…

Large Language Models (LLMs) have shown promising performance in software vulnerability detection, particularly after domain-specific Supervised Fine-Tuning (SFT). However, it remains unclear whether these models genuinely internalize…

LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most…

Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that…

Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

This paper presents a novel methodology for enhancing Automated Program Repair (APR) through synthetic data generation utilizing Large Language Models (LLMs). Current APR systems are constrained by the limited availability of high-quality…

Fault localization is a critical step in software maintenance. Yet, many existing techniques, such as Spectrum-Based Fault Localization (SBFL), rely heavily on the availability of fault-triggering tests to be effective. In practice,…

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their…

Large language models (LLMs) show promise for automating software development by translating requirements into code. However, even advanced prompting workflows like progressive prompting often leave some requirements unmet. Although methods…

LLM applications are AI systems whose nondeterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with…

LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally…

Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can…

Federated Learning (FL) has emerged as a promising solution for collaborative training of large language models (LLMs). However, the integration of LLMs into FL introduces new challenges, particularly concerning the evaluation of LLMs.…

We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitive programming offers a rich benchmark for such evaluation,…

Fault localization is one of the most time-consuming and error-prone parts of software debugging. There are several tools for helping developers in the fault localization process, however, they mostly target programs written in Java and…

Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist…

Monitoring issue tracker submissions is a crucial software maintenance activity. A key goal is the prioritization of high risk, security-related bugs. If such bugs can be recognized early, the risk of propagation to dependent products and…