Large Language Model-Based Agents for Software Engineering: A Survey

The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 106 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.

LLM-Powered Test Case Generation for Detecting Tricky Bugs

Conventional automated test generation tools struggle to generate test oracles and tricky bug-revealing test inputs. Large Language Models (LLMs) can be prompted to produce test inputs and oracles for a program directly, but the precision of the tests can be very low for complex scenarios (only 6.3% based on our experiments). To fill this gap, this paper proposes AID, which combines LLMs with differential testing to generate fault-revealing test inputs and oracles targeting plausibly correct programs (i.e., programs that have passed all the existing tests). In particular, AID selects test inputs that yield diverse outputs on a set of program variants generated by LLMs, then constructs the test oracle based on the outputs. We evaluate AID on two large-scale datasets with tricky bugs: TrickyBugs and EvalPlus, and compare it with three state-of-the-art baselines. The evaluation results show that the recall, precision, and F1 score of AID outperform the state-of-the-art by up to 1.80x, 2.65x, and 1.66x, respectively.

Exploring the Impact of In-Browser Deep Learning Inference on Quality of User Experience and Performance

Deep Learning (DL) is increasingly being integrated into Web applications through a method known as "in-browser inference", where the DL processes occur directly within Web browsers. However, the actual performance of this method and its effect on user experience quality (QoE) is not well-understood. This gap in knowledge necessitates new forms of QoE measurement, going beyond traditional metrics such as page load time. To address this, we conducted the first extensive performance evaluation of in-browser inference. We introduced new metrics for this purpose: responsiveness, smoothness, and inference accuracy. Our thorough study included 9 widely-used DL models and tested them across 50 popular PC Web browsers. The findings show a significant latency issue with in-browser inference: it's on average 16.9 times slower on CPU and 4.9 times slower on GPU than native inference methods. Several factors contribute to this latency, including underused hardware instruction sets, inherent delays in the runtime environment, resource competition within the browser, and inefficiencies in software libraries and GPU abstractions. Moreover, in-browser inference demands a lot of memory, sometimes up to 334.6 times more than the size of the DL models themselves. This excessive memory usage is partly due to suboptimal memory management. Additionally, we noticed that in-browser inference increases the time it takes for graphical user interface (GUI) components to load in web browsers by a significant 67.2\%, which severely impacts the overall QoE for users of web applications that depend on this technology.

Dark-Skin Individuals Are at More Risk on the Street: Unmasking Fairness Issues of Autonomous Driving Systems

This paper conducts fairness testing on automated pedestrian detection, a crucial but under-explored issue in autonomous driving systems. We evaluate eight widely-studied pedestrian detectors across demographic groups on large-scale real-world datasets. To enable thorough fairness testing, we provide extensive annotations for the datasets, resulting in 8,311 images with 16,070 gender labels, 20,115 age labels, and 3,513 skin tone labels. Our findings reveal significant fairness issues related to age and skin tone. The detection accuracy for adults is 19.67% higher compared to children, and there is a 7.52% accuracy disparity between light-skin and dark-skin individuals. Gender, however, shows only a 1.1% difference in detection accuracy. Additionally, we investigate common scenarios explored in the literature on autonomous driving testing, and find that the bias towards dark-skin pedestrians increases significantly under scenarios of low contrast and low brightness. We publicly release the code, data, and results to support future research on fairness in autonomous driving.

An Empirical Study on Fairness Improvement with Multiple Protected Attributes

Existing research mostly improves the fairness of Machine Learning (ML) software regarding a single protected attribute at a time, but this is unrealistic given that many users have multiple protected attributes. This paper conducts an extensive study of fairness improvement regarding multiple protected attributes, covering 11 state-of-the-art fairness improvement methods. We analyze the effectiveness of these methods with different datasets, metrics, and ML models when considering multiple protected attributes. The results reveal that improving fairness for a single protected attribute can largely decrease fairness regarding unconsidered protected attributes. This decrease is observed in up to 88.3% of scenarios (57.5% on average). More surprisingly, we find little difference in accuracy loss when considering single and multiple protected attributes, indicating that accuracy can be maintained in the multiple-attribute paradigm. However, the effect on precision and recall when handling multiple protected attributes is about 5 times and 8 times that of a single attribute. This has important implications for future fairness research: reporting only accuracy as the ML performance metric, which is currently common in the literature, is inadequate.

Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey

This paper provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning (ML) models. We collect a total of 234 publications concerning bias mitigation for ML classifiers. These methods can be distinguished based on their intervention procedure (i.e., pre-processing, in-processing, post-processing) and the technology they apply. We investigate how existing bias mitigation methods are evaluated in the literature. In particular, we consider datasets, metrics and benchmarking. Based on the gathered insights (e.g., what is the most popular fairness metric? How many datasets are used for evaluating bias mitigation methods?). We hope to support practitioners in making informed choices when developing and evaluating new bias mitigation methods.

A Comprehensive Empirical Study of Bias Mitigation Methods for Software Fairness

Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical evaluation of 17 representative bias mitigation methods, evaluated with 12 Machine Learning (ML) performance metrics, 4 fairness metrics, and 24 types of fairness-performance trade-off assessment, applied to 8 widely-adopted benchmark software decision/prediction tasks. The empirical coverage is comprehensive, covering the largest numbers of bias mitigation methods, evaluation metrics, and fairness-performance trade-off measures compared to previous work on this important operational software characteristic. We find that (1) the bias mitigation methods significantly decrease the values reported by all ML performance metrics (including those not considered in previous work) in a large proportion of the scenarios studied (42%~75% according to different ML performance metrics); (2) the bias mitigation methods achieve fairness improvement in only approximately 50% over all scenarios and metrics (ranging between 29%~59% according to the metric used to asses bias/fairness); (3) the bias mitigation methods have a poor fairness-performance trade-off or even lead to decreases in both fairness and ML performance in 37% of the scenarios; (4) the effectiveness of the bias mitigation methods depends on tasks, models, and fairness and ML performance metrics, and there is no 'silver bullet' bias mitigation method demonstrated to be effective for all scenarios studied. The best bias mitigation method that we find outperforms other methods in only 29% of the scenarios. We have made publicly available the scripts and data used in this study in order to allow for future replication and extension of our work.

Learning point embedding for 3D data processing

Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods are essentially spatial relationship processing networks. In this paper, we take a different approach. Our architecture, named PE-Net, learns the representation of point clouds in high-dimensional space, and encodes the unordered input points to feature vectors, which standard 2D CNNs can be applied to. The recommended network can adapt to changes in the number of input points which is the limit of current methods. Experiments show that in the tasks of classification and part segmentation, PE-Net achieves the state-of-the-art performance in multiple challenging datasets, such as ModelNet and ShapeNetPart.

Emojis Predict Dropouts of Remote Workers: An Empirical Study of Emoji Usage on GitHub

Emotions at work have long been identified as critical signals of work motivations, status, and attitudes, and as predictors of various work-related outcomes. For example, harmonious passion increases commitment at work but stress reduces sustainability and leads to burnouts. When more and more employees work remotely, these emotional and mental health signals of workers become harder to observe through daily, face-to-face communications. The use of online platforms to communicate and collaborate at work provides an alternative channel to monitor the emotions of workers. This paper studies how emojis, as non-verbal cues in online communications, can be used for such purposes. In particular, we study how the developers on GitHub use emojis in their work-related activities. We show that developers have diverse patterns of emoji usage, which highly correlate to their working status including activity levels, types of work, types of communications, time management, and other behavioral patterns. Developers who use emojis in their posts are significantly less likely to dropout from the online work platform. Surprisingly, solely using emoji usage as features, standard machine learning models can predict future dropouts of developers at a satisfactory accuracy.

An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications

Deep Learning (DL) is finding its way into a growing number of mobile software applications. These software applications, named as DL based mobile applications (abbreviated as mobile DL apps) integrate DL models trained using large-scale data with DL programs. A DL program encodes the structure of a desirable DL model and the process by which the model is trained using training data. Due to the increasing dependency of current mobile apps on DL, software engineering (SE) for mobile DL apps has become important. However, existing efforts in SE research community mainly focus on the development of DL models and extensively analyze faults in DL programs. In contrast, faults related to the deployment of DL models on mobile devices (named as deployment faults of mobile DL apps) have not been well studied. Since mobile DL apps have been used by billions of end users daily for various purposes including for safety-critical scenarios, characterizing their deployment faults is of enormous importance. To fill the knowledge gap, this paper presents the first comprehensive study on the deployment faults of mobile DL apps. We identify 304 real deployment faults from Stack Overflow and GitHub, two commonly used data sources for studying software faults. Based on the identified faults, we construct a fine-granularity taxonomy consisting of 23 categories regarding to fault symptoms and distill common fix strategies for different fault types. Furthermore, we suggest actionable implications and research avenues that could further facilitate the deployment of DL models on mobile devices.