Chengxi Pan | Searcharxiv

arXiv2026

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understanding. Recent methods attempt to mitigate this limitation through pre-repair repository exploration; however, their fix-driven strategies explore repositories without identifying the agent's knowledge gaps, often yielding imprecise context that fails to bridge the underlying understanding deficit. In this paper, we propose ACQUIRE, a QA-driven framework for software issue resolution. Mirroring how experienced developers first comprehend unfamiliar code before attempting a fix, ACQUIRE explicitly acquires repository knowledge prior to repair. The framework decouples knowledge acquisition from patch generation through two stages: in the first stage, a Questioner and an Answerer collaborate to acquire structured repository knowledge, where the Questioner poses targeted questions and the Answerer produces evidence-grounded answers through autonomous exploration; in the second stage, the Resolver leverages the resulting QA knowledge to generate informed patches. By transforming implicit knowledge gaps into explicit, factually reliable understanding, ACQUIRE accelerates knowledge-intensive repair stages and enables more accurate resolution. Experiments on SWE-bench Verified demonstrate that ACQUIRE consistently outperforms representative pre-repair methods, raising Pass@1 by up to 4.4 percentage points with modest additional cost and time.

cs.SE↗

arXiv2024

WarpAdam: A new Adam optimizer based on Meta-Learning approach

Optimal selection of optimization algorithms is crucial for training deep learning models. The Adam optimizer has gained significant attention due to its efficiency and wide applicability. However, to enhance the adaptability of optimizers across diverse datasets, we propose an innovative optimization strategy by integrating the 'warped gradient descend'concept from Meta Learning into the Adam optimizer. In the conventional Adam optimizer, gradients are utilized to compute estimates of gradient mean and variance, subsequently updating model parameters. Our approach introduces a learnable distortion matrix, denoted as P, which is employed for linearly transforming gradients. This transformation slightly adjusts gradients during each iteration, enabling the optimizer to better adapt to distinct dataset characteristics. By learning an appropriate distortion matrix P, our method aims to adaptively adjust gradient information across different data distributions, thereby enhancing optimization performance. Our research showcases the potential of this novel approach through theoretical insights and empirical evaluations. Experimental results across various tasks and datasets validate the superiority of our optimizer that integrates the 'warped gradient descend' concept in terms of adaptability. Furthermore, we explore effective strategies for training the adaptation matrix P and identify scenarios where this method can yield optimal results. In summary, this study introduces an innovative approach that merges the 'warped gradient descend' concept from Meta Learning with the Adam optimizer. By introducing a learnable distortion matrix P within the optimizer, we aim to enhance the model's generalization capability across diverse data distributions, thus opening up new possibilities in the field of deep learning optimization.

cs.LG↗