arXiv subjects

Sungmin Kang

Publications and source records attributed to Sungmin Kang.

At least 19 recordsLinked to original sources

arXiv2026

Skills for the future software profession: beyond agentic AI!

As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineers? To identify where software engineering is headed and thus what skills will be needed, we summarize the results of two round-tables with researchers and industrial practitioners, held in 2026 in New York and Singapore. One key finding is that verification and validation is increasing in importance as agents handle implementation, as highlighted by anecdotes from the events. From our observations, we identify the skills developers need in the agentic era of development, with implications for training and educating future software engineers in coming years.

cs.SE↗

arXiv2026

ExplainBench: Evaluating Code Explanations from Agents

Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes, spanning tens to hundreds of lines. This makes manual review of agent results increasingly infeasible, leading developers to turn to explanations to understand enacted changes. Despite this, there are no benchmarks that evaluate the trustworthiness of agent-generated explanations. To bridge this gap, we propose ExplainBench, a benchmark to automatically evaluate explanations from coding agents. ExplainBench is based on the intuition that informative explanations should enable an LLM to correctly answer questions, allowing quantitative comparison of explanation quality between agents. With this observation, we construct a suite of questions that evaluates whether explanations accurately describe (1) the intended behavior of buggy code and (2) the effect of applying the agent patch itself. Experiments first reveal that explanation quality is a distinct axis of agent evaluation: ExplainBench ranks agents differently from the widely-used SWE-bench Verified benchmark. A deeper breakdown of explanation quality in agents shows frequent problems in explanations, such that explanations often claim that a patch is correct when it is not. Based on this insight, we implement and evaluate an explanation audit agent which runs additional tests to validate and refine explanations. This agent improved the explanations of all evaluated agents, demonstrating agent explanations can be automatically made more trustworthy.

cs.SE↗

arXiv2026

VeriGrey: Greybox Agent Validation

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results obtained by invoking several external tools. The autonomous interactions with the external environment introduce critical security risks. In this paper, we present a grey-box approach to explore diverse behaviors and uncover security risks in LLM agents. Our approach VeriGrey uses the sequence of tools invoked as a feedback function to drive the testing process. This helps uncover infrequent but dangerous tool invocations that cause unexpected agent behavior. As mutation operators in the testing process, we mutate prompts to design pernicious injection prompts. This is carefully accomplished by linking the task of the agent to an injection task, so that the injection task becomes a necessary step of completing the agent functionality. Comparing our approach with a black-box baseline on the well-known AgentDojo benchmark, VeriGrey achieves 33% additional efficacy in finding indirect prompt injection vulnerabilities with a GPT-4.1 back-end. We also conduct real-world case studies with the widely used coding agent Gemini CLI, and the well-known OpenClaw personal assistant. VeriGrey finds prompts inducing several attack scenarios that could not be identified by black-box approaches. In OpenClaw, by constructing a conversation agent which employs mutational fuzz testing as needed, VeriGrey is able to discover malicious skill variants from 10 malicious skills (with 10/10= 100% success rate on the Kimi-K2.5 LLM backend, and 9/10= 90% success rate on Opus 4.6 LLM backend). This demonstrates the value of a dynamic approach like VeriGrey to test agents, and to eventually lead to an agent assurance framework.

cs.AI↗

arXiv2026

Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning

Expensive communication cost is a common performance bottleneck in Federated Learning (FL), which makes it less appealing in real-world applications. Many communication-efficient FL methods focus on discarding a part of model updates mostly based on gradient magnitude. In this study, we find that recycling previous updates, rather than simply dropping them, more effectively reduces the communication cost while maintaining FL performance. We propose FedLUAR, a Layer-wise Update Aggregation with Recycling scheme for communication-efficient FL. We first define a useful metric that quantifies the extent to which the aggregated gradients influences the model parameter values in each layer. FedLUAR selects a few layers based on the metric and recycles their previous updates on the server side. Our extensive empirical study demonstrates that the update recycling scheme significantly reduces the communication cost while maintaining model accuracy. For example, our method achieves nearly the same AG News accuracy as FedAvg, while reducing the communication cost to just 17%.

cs.LG↗

arXiv2026

AutoCodeSherpa: Symbolic Explanations in AI Coding Agents

Large language model (LLM) agents integrate external tools with one or more LLMs to accomplish specific tasks. Agents have rapidly been adopted by developers, and they are starting to be deployed in industrial workflows, such as their use to fix static analysis issues from the widely used SonarQube static analyzer. However, the growing importance of agents means their actions carry greater impact and potential risk. Thus, to use them at scale, an additional layer of trust and evidence is necessary. This work presents AutoCodeSherpa, a technique that provides explanations of software issues in the form of symbolic formulae. Inspired by the reachability, infection, and propagation model of software faults, the explanations are composed of input, infection, and output conditions, collectively providing a specification of the issue. In practice, the symbolic explanation is implemented as a combination of a property-based test (PBT) and program-internal symbolic expressions. Critically, this means our symbolic explanations are executable and can be automatically evaluated, unlike natural language explanations. Experiments show the generated conditions are highly accurate. For example, input conditions from AutoCodeSherpa had an accuracy of 85.7%. This high accuracy makes symbolic explanations particularly useful in two scenarios. First, the explanations can be used in automated issue resolution environments to decide whether to accept or reject patches from issue resolution agents; AutoCodeSherpa could reject 2x as many incorrect patches as baselines did. Secondly, as agentic AI approaches continue to develop, program analysis driven explanations like ours can be provided to other LLM-based repair techniques which do not employ analysis to improve their output. In our experiments, our symbolic explanations could improve the plausible patch generation rate of the Agentless technique by 60%.

cs.SE↗

arXiv2025

Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL

Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses to improve accuracy, such as coverage profiling or mutation testing. However, for large industrial software, measuring coverage for every execution is prohibitively expensive, making the use of such techniques difficult. To address these issues and apply FL in an industrial setting, this paper proposes AutoCrashFL, an LLM agent for the localization of crashes that only requires the crashdump from the Program Under Test (PUT) and access to the repository of the corresponding source code. We evaluate AutoCrashFL against real-world crashes of SAP HANA, an industrial software project consisting of more than 35 million lines of code. Experiments reveal that AutoCrashFL is more effective in localization, as it identified 30% crashes at the top, compared to 17% achieved by the baseline. Through thorough analysis, we find that AutoCrashFL has attractive practical properties: it is relatively more effective for complex bugs, and it can indicate confidence in its results. Overall, these results show the practicality of LLM agent deployment on an industrial scale.

cs.SE↗

arXiv2025

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering

Uncertainty Quantification (UQ) research has primarily focused on closed-book factual question answering (QA), while contextual QA remains unexplored, despite its importance in real-world applications. In this work, we focus on UQ for the contextual QA task and propose a theoretically grounded approach to quantify epistemic uncertainty. We begin by introducing a task-agnostic, token-level uncertainty measure defined as the cross-entropy between the predictive distribution of the given model and the unknown true distribution. By decomposing this measure, we isolate the epistemic component and approximate the true distribution by a perfectly prompted, idealized model. We then derive an upper bound for epistemic uncertainty and show that it can be interpreted as semantic feature gaps in the given model's hidden representations relative to the ideal model. We further apply this generic framework to the contextual QA task and hypothesize that three features approximate this gap: context-reliance (using the provided context rather than parametric knowledge), context comprehension (extracting relevant information from context), and honesty (avoiding intentional lies). Using a top-down interpretability approach, we extract these features by using only a small number of labeled samples and ensemble them to form a robust uncertainty score. Experiments on multiple QA benchmarks in both in-distribution and out-of-distribution settings show that our method substantially outperforms state-of-the-art unsupervised (sampling-free and sampling-based) and supervised UQ methods, achieving up to a 13-point PRR improvement while incurring a negligible inference overhead.

cs.CL↗

arXiv2025

Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions

The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for hallucination detection.

cs.CL↗

arXiv2025

GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation

Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they maximize the absolute size of the updates without regard to the parameters' original scale, the resulting changes in model behavior can be minimal. In contrast, we maximize updates relative to each parameter's scale, yielding more meaningful downstream adaptation. We propose Gradient-to-Weight Ratio and Entropy-guided Masking (GEM), a parameter scale-aware, distribution-sensitive sparse fine-tuning framework. GEM prioritizes parameters whose updates are significant in proportion to their initial pre-trained values. It also adaptively determines how many parameters to tune at each layer based on the entropy of parameter values, thereby making the most effective use of the computational budget in PEFT. Our empirical study demonstrates the efficacy of GEM on both general-domain tasks (GLUE and SuperGLUE) and domain-specific tasks (GSM8k and MBPP), achieving up to a 1.6% improvement in fine-tuning accuracy over full fine-tuning while updating only 0.1% of model parameters.

cs.LG↗

arXiv2025

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs

Generative Large Language Models (LLMs)inevitably produce untruthful responses. Accurately predicting the truthfulness of these outputs is critical, especially in high-stakes settings. To accelerate research in this domain and make truthfulness prediction methods more accessible, we introduce TruthTorchLM an open-source, comprehensive Python library featuring over 30 truthfulness prediction methods, which we refer to as Truth Methods. Unlike existing toolkits such as Guardrails, which focus solely on document-grounded verification, or LM-Polygraph, which is limited to uncertainty-based methods, TruthTorchLM offers a broad and extensible collection of techniques. These methods span diverse tradeoffs in computational cost, access level (e.g., black-box vs white-box), grounding document requirements, and supervision type (self-supervised or supervised). TruthTorchLM is seamlessly compatible with both HuggingFace and LiteLLM, enabling support for locally hosted and API-based models. It also provides a unified interface for generation, evaluation, calibration, and long-form truthfulness prediction, along with a flexible framework for extending the library with new methods. We conduct an evaluation of representative truth methods on three datasets, TriviaQA, GSM8K, and FactScore-Bio. The code is available at https://github.com/Ybakman/TruthTorchLM

cs.CL↗

arXiv2025

Reconsidering LLM Uncertainty Estimation Methods in the Wild

Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed, most existing studies evaluate them in isolated short-form QA settings using threshold-independent metrics such as AUROC or PRR. However, real-world deployment of UE methods introduces several challenges. In this work, we systematically examine four key aspects of deploying UE methods in practical settings. Specifically, we assess (1) the sensitivity of UE methods to decision threshold selection, (2) their robustness to query transformations such as typos, adversarial prompts, and prior chat history, (3) their applicability to long-form generation, and (4) strategies for handling multiple UE scores for a single query. Our evaluations on 19 UE methods reveal that most of them are highly sensitive to threshold selection when there is a distribution shift in the calibration dataset. While these methods generally exhibit robustness against previous chat history and typos, they are significantly vulnerable to adversarial prompts. Additionally, while existing UE methods can be adapted for long-form generation through various strategies, there remains considerable room for improvement. Lastly, ensembling multiple UE scores at test time provides a notable performance boost, which highlights its potential as a practical improvement strategy. Code is available at: https://github.com/duygunuryldz/uncertainty_in_the_wild.

cs.LG↗

arXiv2025

Predictive Prompt Analysis

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented, also known as prompting. However, prompting well is challenging, as it has been difficult to uncover principles behind prompting -- generally, trial-and-error is the most common way of improving prompts, despite its significant computational cost. In this context, we argue it would be useful to perform `predictive prompt analysis', in which an automated technique would perform a quick analysis of a prompt and predict how the LLM would react to it, relative to a goal provided by the user. As a demonstration of the concept, we present Syntactic Prevalence Analyzer (SPA), a predictive prompt analysis approach based on sparse autoencoders (SAEs). SPA accurately predicted how often an LLM would generate target syntactic structures during code synthesis, with up to 0.994 Pearson correlation between the predicted and actual prevalence of the target structure. At the same time, SPA requires only 0.4\% of the time it takes to run the LLM on a benchmark. As LLMs are increasingly used during and integrated into modern software development, our proposed predictive prompt analysis concept has the potential to significantly ease the use of LLMs for both practitioners and researchers.

cs.SE↗

arXiv2025

COSMosFL: Ensemble of Small Language Models for Fault Localisation

LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, can hinder wider adoption due to security issues as well as financial cost and environmental impact. Recently, a number of open source Small Language Models (SLMs) are being released and gaining traction. While SLMs are smaller, more energy-efficient, and therefore easier to locally deploy, they tend to show worse performance when compared to larger closed LLMs. We present COSMos, a task-level LLM ensemble technique that uses voting mechanism, to provide a broader range of choice between SLMs and LLMs. We instantiate COSMos with an LLM-based Fault Localisation technique, AutoFL, and report the cost-benefit trade-off between LLM accuracy and various costs such as energy consumption, inference time, and the number of tokens used. An empirical evaluation using Defects4J shows that COSMos can build effective ensembles that can achieve Pareto-optimality in terms of FL accuracy and inference cost, when compared to individual models.

cs.SE↗

arXiv2024

Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths

Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, a predictive model for self-consistency based LLM inferences, and empirically evaluate it using AutoFL, a recently proposed LLM-based fault localisation technique, as the target technique that uses self-consistency. Lachesis converts collected reasoning paths from AutoFL using specifically designed reasoning path representations, and trains LSTM and GCN models to predict whether a given set of reasoning paths would result in a correct answer. The results suggest that Lachesis can predict the correctness of answers with a precision of up to 0.8136, highlighting the possibility of training a predictive model that can allow early termination of inferences that are not likely to be successful.

cs.SE↗

arXiv2024

Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects

Many works have recently proposed the use of Large Language Model (LLM) based agents for performing `repository level' tasks, loosely defined as a set of tasks whose scopes are greater than a single file. This has led to speculation that the orchestration of these repository-level tasks could lead to software engineering agents capable of performing almost independently of human intervention. However, of the suite of tasks that would need to be performed by this autonomous software engineering agent, we argue that one important task is missing, which is to fulfil project level dependency by installing other repositories. To investigate the feasibility of this repository level installation task, we introduce a benchmark of of repository installation tasks curated from 40 open source Python projects, which includes a ground truth installation process for each target repository. Further, we propose Installamatic, an agent which aims to perform and verify the installation of a given repository by searching for relevant instructions from documentation in the repository. Empirical experiments reveal that that 55% of the studied repositories can be automatically installed by our agent at least one out of ten times. Through further analysis, we identify the common causes for our agent's inability to install a repository, discuss the challenges faced in the design and implementation of such an agent and consider the implications that such an agent could have for developers.

cs.SE↗

arXiv2024

Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer

Understanding the morphological structure of medical images and precisely segmenting the region of interest or abnormality is an important task that can assist in diagnosis. However, the unique properties of medical imaging make clear segmentation difficult,and the high cost and time-consuming task of labeling leads to a coarse-grained representation of ground truth. Facing with these problems, we propose a novel Diffusion Transformer Segmentation (DTS) model for robust segmentation in the presence of noise. We propose an alternative to the dominant Denoising U-Net encoder through experiments applying a transformer architecture, which captures global dependency through self-attention. Additionally, we propose k-neighbor label smoothing, reverse boundary attention, and self-supervised learning with morphology-driven learning to improve the ability to identify complex structures. Our model, which analyzes the morphological representation of images, shows better results than the previous models in various medical imaging modalities, including CT, MRI, and lesion images.

cs.CV↗

arXiv2024

A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization

Fault Localization (FL), in which a developer seeks to identify which part of the code is malfunctioning and needs to be fixed, is a recurring challenge in debugging. To reduce developer burden, many automated FL techniques have been proposed. However, prior work has noted that existing techniques fail to provide rationales for the suggested locations, hindering developer adoption of these techniques. With this in mind, we propose AutoFL, a Large Language Model (LLM)-based FL technique that generates an explanation of the bug along with a suggested fault location. AutoFL prompts an LLM to use function calls to navigate a repository, so that it can effectively localize faults over a large software repository and overcome the limit of the LLM context length. Extensive experiments on 798 real-world bugs in Java and Python reveal AutoFL improves method-level acc@1 by up to 233.3% over baselines. Furthermore, developers were interviewed on their impression of AutoFL-generated explanations, showing that developers generally liked the natural language explanations of AutoFL, and that they preferred reading a few, high-quality explanations instead of many.

cs.SE↗

arXiv2024

Identifying Inaccurate Descriptions in LLM-generated Code Comments via Test Execution

Software comments are critical for human understanding of software, and as such many comment generation techniques have been proposed. However, we find that a systematic evaluation of the factual accuracy of generated comments is rare; only subjective accuracy labels have been given. Evaluating comments generated by three Large Language Models (LLMs), we find that even for the best-performing LLM, roughly a fifth of its comments contained demonstrably inaccurate statements. While it seems code-comment consistency detection techniques should be able to detect inaccurate comments, we perform experiments demonstrating they have no statistically significant relationship with comment accuracy, underscoring the substantial difficulty of this problem. To tackle this, we propose the concept of document testing, in which a document is verified by using an LLM to generate tests based on the document, running those tests, and observing whether they pass or fail. Furthermore, we implement our concept to verify Java comments. Experiments demonstrate that our approach has a robust statistical relationship with comment accuracy, making headway into a problem where prior techniques failed. Qualitative evaluation also reveals the promise of our approach in gaining developer trust, while highlighting the limitations of our current implementation.

cs.SE↗