arXiv subjects

Kaiwei Lin

Publications and source records attributed to Kaiwei Lin.

4 recordsLinked to original sources

arXiv2026

REAgent: Requirement-Driven LLM Agents for Software Issue Resolution

Issue resolution aims to automatically generate patches from given issue descriptions and has attracted significant attention with the rapid advancement of large language models (LLMs). However, due to the complexity of software issues and codebases, LLM-generated patches often fail to resolve corresponding issues. Although various advanced techniques have been proposed with carefully designed tools and workflows, they typically treat issue descriptions as direct inputs and largely overlook their quality (e.g., missing critical context or containing ambiguous information), which hinders LLMs from accurate understanding and resolution. To address this limitation, we draw on principles from software requirements engineering and propose REAgent, a requirement-driven LLM agent framework that introduces issue-oriented requirements as structured task specifications to better guide patch generation. Specifically, REAgent automatically constructs structured and information-rich issue-oriented requirements, identifies low-quality requirements, and iteratively refines them to improve patch correctness. We conduct comprehensive experiments on three widely used benchmarks using two advanced LLMs, comparing against five representative or state-of-the-art baselines. The results demonstrate that REAgent consistently outperforms all baselines, achieving an average improvement of 17.40% in terms of the number of successfully-resolved issues (% Resolved).

cs.SE↗

arXiv2026

SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that remain fixed throughout the decoding process, failing to adapt to the varying prediction difficulty across generation steps. This leads to suboptimal acceptance lengths and limited speedup. In this paper, we propose SAGE, a novel framework that dynamically adjusts the speculation tree structure based on real-time prediction uncertainty. Our key insight is that output entropy serves as a natural confidence indicator with strong temporal correlation across decoding steps. SAGE constructs deeper-narrower trees for high-confidence predictions to maximize speculation depth, and shallower-wider trees for uncertain predictions to diversify exploration. SAGE improves acceptance lengths and achieves faster acceleration compared to static tree baselines. Experiments on multiple benchmarks demonstrate the effectiveness of SAGE: without any loss in output quality, it delivers up to $3.36\times$ decoding speedup for LLaVA-OneVision-72B and $3.18\times$ for Qwen2.5-VL-72B.

cs.CV↗

arXiv2025

A Survey of Reinforcement Learning for Software Engineering

Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the rising demand for automation have motivated researchers to apply RL to a broad range of tasks, from software design and development to quality assurance and maintenance. Despite growing research in RL-for-SE, there remains a lack of a comprehensive and systematic survey of this evolving field. To address this gap, we reviewed 115 peer-reviewed studies published across 22 premier SE venues since the introduction of DRL. We conducted a comprehensive analysis of publication trends, categorized SE topics and RL algorithms, and examined key factors such as dataset usage, model design and optimization, and evaluation practices. Furthermore, we identified open challenges and proposed future research directions to guide and inspire ongoing work in this evolving area. To summarize, this survey offers the first systematic mapping of RL applications in software engineering, aiming to support both researchers and practitioners in navigating the current landscape and advancing the field. Our artifacts are publicly available: https://github.com/KaiWei-Lin-lanina/RL4SE.

cs.SE↗

arXiv2024

Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients. However, can gradient perturbation protection mechanisms truly defend against all gradient leakage attacks? In this paper, we present the first attempt to break the shield of gradient perturbation protection in Federated Learning for the extraction of private information. We focus on common noise distributions, specifically Gaussian and Laplace, and apply our approach to DNN and CNN models. We introduce Mjolnir, a perturbation-resilient gradient leakage attack that is capable of removing perturbations from gradients without requiring additional access to the original model structure or external data. Specifically, we leverage the inherent diffusion properties of gradient perturbation protection to develop a novel diffusion-based gradient denoising model for Mjolnir. By constructing a surrogate client model that captures the structure of perturbed gradients, we obtain crucial gradient data for training the diffusion model. We further utilize the insight that monitoring disturbance levels during the reverse diffusion process can enhance gradient denoising capabilities, allowing Mjolnir to generate gradients that closely approximate the original, unperturbed versions through adaptive sampling steps. Extensive experiments demonstrate that Mjolnir effectively recovers the protected gradients and exposes the Federated Learning process to the threat of gradient leakage, achieving superior performance in gradient denoising and private data recovery.

cs.LG↗