arXiv subjects

Alex Mathai

Publications and source records attributed to Alex Mathai.

12 recordsLinked to original sources

arXiv2026

TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation. In this work, we show that the cause lies in the agent's own search process: while iterating toward a passing solution, an agent accumulates speculative edits, abandoned hypotheses, and temporary changes that persist into the final patch. This may seem harmless for a single patch, but the problem compounds as agents take responsibility for ever-larger portions of a codebase-a codebase that was once minimal and well-maintained slowly accumulates redundancy faster than it can be cleaned up, drifting to a state that is harder to maintain. Given the magnitude of this problem, we take a step towards alleviating this issue. First, we formally define this phenomenon as CodeSlop-the residual and functionally unnecessary edits commonly seen in AI-generated code. We then introduce our algorithm TRIM (Trajectory-guided Redundancy Identification and Minimization). Rather than minimizing CodeSlop directly, TRIM instead minimizes agent trajectories. As we show empirically, this indirect technique of minimizing CodeSlop is highly effective: TRIM cuts CodeSlop by 17.9%-32.9% across agentic scaffolds, with negligible performance regression. TRIM is also highly efficient, requiring roughly half the validation cost of algorithmic baselines such as Delta Debugging.

cs.SE↗

arXiv2026

Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All

Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel crash-resolution, their evaluation benchmarks are usually static and thus, do not capture the evolving nature of the Linux kernel, and suffer from potential data contamination due to LLM knowledge cutoffs. To address the above problem, we present (i) Live-kBench, an evaluation framework for self-evolving benchmarks that continuously scrapes and evaluates agents on freshly discovered kernel bugs, and (ii) kEnv, an agent-agnostic standardized crash-resolution environment for kernel compilation, execution, and feedback. This design decouples agent workflows from heavy-weight execution, enabling fair and scalable comparison across diverse agent frameworks under identical conditions. To this end, we curate an inaugural dataset of 534 Linux kernel bugs and empirically demonstrate a significant performance gap, with agents achieving up to 25% higher equivalent patch rate on bugs fixed before the LLM knowledge cutoff. Using kEnv, we benchmark three state-of-the-art agents, showing that they resolve 74% of crashes on the first attempt (plausible patches); however only ~20% of generated patches closely match developer fixes. Additionally, exposing crash resolution feedback improves crash resolution rate by 29%. Live-kBench provides the community with an evaluation infrastructure for self-evolving benchmarks that is both time and attribute sensitive; complete with a public dashboard to track agent progress on Linux kernel bugs.

cs.SE↗

arXiv2025

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement

Large Language Models (LLMs) have recently shown strong potential in automatic program repair (APR), especially in repository-level settings where the goal is to generate patches based on natural language issue descriptions, large codebases, and regression tests. However, despite their promise, current LLM-based APR techniques often struggle to produce correct fixes due to limited understanding of code context and over-reliance on incomplete test suites. As a result, they frequently generate Draft Patches-partially correct patches that either incompletely address the bug or overfit to the test cases. In this work, we propose a novel patch refinement framework, Refine, that systematically transforms Draft Patches into correct ones. Refine addresses three key challenges: disambiguating vague issue and code context, diversifying patch candidates through test-time scaling, and aggregating partial fixes via an LLM-powered code review process. We implement Refine as a general refinement module that can be integrated into both open-agent-based and workflow-based APR systems. Our evaluation on the SWE-Bench Lite benchmark shows that Refine achieves state-of-the-art results among workflow-based approaches and approaches the best-known performance across all APR categories. Specifically, Refine boosts AutoCodeRover's performance by 14.67%, achieving a score of 51.67% and surpassing all prior baselines. On SWE-Bench Verified, Refine improves the resolution rate by 12.2%, and when integrated across multiple APR systems, it yields an average improvement of 14%-demonstrating its broad effectiveness and generalizability. These results highlight the effectiveness of refinement as a missing component in current APR pipelines and the potential of agentic collaboration in closing the gap between near-correct and correct patches. We also open source our code.

cs.SE↗

arXiv2025

SemAgent: A Semantics Aware Program Repair Agent

Large Language Models (LLMs) have shown impressive capabilities in downstream software engineering tasks such as Automated Program Repair (APR). In particular, there has been a lot of research on repository-level issue-resolution benchmarks such as SWE-Bench. Although there has been significant progress on this topic, we notice that in the process of solving such issues, existing agentic systems tend to hyper-localize on immediately suspicious lines of code and fix them in isolation, without a deeper understanding of the issue semantics, code semantics, or execution semantics. Consequently, many existing systems generate patches that overfit to the user issue, even when a more general fix is preferable. To address this limitation, we introduce SemAgent, a novel workflow-based procedure that leverages issue, code, and execution semantics to generate patches that are complete - identifying and fixing all lines relevant to the issue. We achieve this through a novel pipeline that (a) leverages execution semantics to retrieve relevant context, (b) comprehends issue-semantics via generalized abstraction, (c) isolates code-semantics within the context of this abstraction, and (d) leverages this understanding in a two-stage architecture: a repair stage that proposes fine-grained fixes, followed by a reviewer stage that filters relevant fixes based on the inferred issue-semantics. Our evaluations show that our methodology achieves a solve rate of 44.66% on the SWEBench-Lite benchmark beating all other workflow-based approaches, and an absolute improvement of 7.66% compared to our baseline, which lacks such deep semantic understanding. We note that our approach performs particularly well on issues requiring multi-line reasoning (and editing) and edge-case handling, suggesting that incorporating issue and code semantics into APR pipelines can lead to robust and semantically consistent repairs.

cs.SE↗

arXiv2025

Incremental Analysis of Legacy Applications Using Knowledge Graphs for Application Modernization

Industries such as banking, telecom, and airlines - o6en have large so6ware systems that are several decades old. Many of these systems are written in old programming languages such as COBOL, PL/1, Assembler, etc. In many cases, the documentation is not updated, and those who developed/designed these systems are no longer around. Understanding these systems for either modernization or even regular maintenance has been a challenge. An extensive application may have natural boundaries based on its code dependencies and architecture. There are also other logical boundaries in an enterprise setting driven by business functions, data domains, etc. Due to these complications, the system architects generally plan their modernization across these logical boundaries in parts, thereby adopting an incremental approach for the modernization journey of the entire system. In this work, we present a so6ware system analysis tool that allows a subject ma=er expert (SME) or system architect to analyze a large so6ware system incrementally. We analyze the source code and other artifacts (such as data schema) to create a knowledge graph using a customizable ontology/schema. Entities and relations in our ontology can be defined for any combination of programming languages and platforms. Using this knowledge graph, the analyst can then define logical boundaries around dependent Entities (e.g. Programs, Transactions, Database Tables etc.). Our tool then presents different views showcasing the dependencies from the newly defined boundary to/from the other logical groups of the system. This exercise is repeated interactively to 1) Identify the Entities and groupings of interest for a modernization task and 2) Understand how a change in one part of the system may affect the other parts. To validate the efficacy of our tool, we provide an initial study of our system on two client applications.

cs.SE↗

arXiv2025

kAgent: An execution-guided crash resolution agent for the Linux kernel

Fuzzing frameworks like syzkaller have uncovered thousands of Linux kernel crashes, many of which are critical and security-sensitive. However, the ability to rapidly repair these crashes has not kept pace, particularly given the complexity and low-level nature of kernel code. Predominantly targeting user-space applications, existing LLM-based program repair techniques are not tailored to the unique challenges posed by kernel fuzz bugs-such as the absence of natural language bug reports, lack of exhaustive test oracles, and highly specialized crash artifacts. Thus, in this work, we first identify the prevalent bottlenecks that generic agents struggle with in complex systems such as the Linux kernel. Guided by these findings, we then build kAgent, a workflow-based agent inspired by how kernel developers diagnose and fix bugs, and kGym++, the co-designed toolstack supporting kAgent's requests. kAgent inspects relevant execution logs, generates execution-grounded natural language hypotheses, synthesizes candidate patches, validates patches through crash reproduction, and iteratively refines its reasoning. We ablate these agentic system features in kAgent and quantitatively analyze their contributions to the overall performance. We also report our experience on building agents for kernel crash repair. Although derived from this work on Linux, we note that our experience applies broadly to fuzzing-discovered bugs in complex systems software. We evaluate kAgent on kBenchSyz and show that it can repair up to 54.5% of crashes without localization and 65% with correct file hints. We also show kAgent's generalization on a few wild Syzkaller bugs, and how different patch types offer varying utility to developers who debug complex system software.

cs.SE↗

arXiv2024

CodeSAM: Source Code Representation Learning by Infusing Self-Attention with Multi-Code-View Graphs

Machine Learning (ML) for software engineering (SE) has gained prominence due to its ability to significantly enhance the performance of various SE applications. This progress is largely attributed to the development of generalizable source code representations that effectively capture the syntactic and semantic characteristics of code. In recent years, pre-trained transformer-based models, inspired by natural language processing (NLP), have shown remarkable success in SE tasks. However, source code contains structural and semantic properties embedded within its grammar, which can be extracted from structured code-views like the Abstract Syntax Tree (AST), Data-Flow Graph (DFG), and Control-Flow Graph (CFG). These code-views can complement NLP techniques, further improving SE tasks. Unfortunately, there are no flexible frameworks to infuse arbitrary code-views into existing transformer-based models effectively. Therefore, in this work, we propose CodeSAM, a novel scalable framework to infuse multiple code-views into transformer-based models by creating self-attention masks. We use CodeSAM to fine-tune a small language model (SLM) like CodeBERT on the downstream SE tasks of semantic code search, code clone detection, and program classification. Experimental results show that by using this technique, we improve downstream performance when compared to SLMs like GraphCodeBERT and CodeBERT on all three tasks by utilizing individual code-views or a combination of code-views during fine-tuning. We believe that these results are indicative that techniques like CodeSAM can help create compact yet performant code SLMs that fit in resource constrained settings.

cs.SE↗

arXiv2024

KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution

Large Language Models (LLMs) are consistently improving at increasingly realistic software engineering (SE) tasks. In real-world software stacks, significant SE effort is spent developing foundational system software like the Linux kernel. Unlike application-level software, a systems codebase like Linux is multilingual (low-level C/Assembly/Bash/Rust); gigantic (>20 million lines); critical (impacting billions of devices worldwide), and highly concurrent (involving complex multi-threading). To evaluate if ML models are useful while developing such large-scale systems-level software, we introduce kGym (a platform) and kBench (a dataset). The kGym platform provides a SE environment for large-scale experiments on the Linux kernel, including compiling and running kernels in parallel across several virtual machines, detecting operations and crashes, inspecting logs, and querying and patching the code base. We use kGym to facilitate evaluation on kBench, a crash resolution benchmark drawn from real-world Linux kernel bugs. An example bug in kBench contains crashing stack traces, a bug-reproducer file, a developer-written fix, and other associated data. To understand current performance, we conduct baseline experiments by prompting LLMs to resolve Linux kernel crashes. Our initial evaluations reveal that the best performing LLM achieves 0.72% and 5.38% in the unassisted and assisted (i.e., buggy files disclosed to the model) settings, respectively. These results highlight the need for further research to enhance model performance in SE tasks. Improving performance on kBench requires models to master new learning skills, including understanding the cause of crashes and repairing faults, writing memory-safe and hardware-aware code, and understanding concurrency. As a result, this work opens up multiple avenues of research at the intersection of machine learning and systems software.

cs.SE↗

arXiv2023

COMEX: A Tool for Generating Customized Source Code Representations

Learning effective representations of source code is critical for any Machine Learning for Software Engineering (ML4SE) system. Inspired by natural language processing, large language models (LLMs) like Codex and CodeGen treat code as generic sequences of text and are trained on huge corpora of code data, achieving state of the art performance on several software engineering (SE) tasks. However, valid source code, unlike natural language, follows a strict structure and pattern governed by the underlying grammar of the programming language. Current LLMs do not exploit this property of the source code as they treat code like a sequence of tokens and overlook key structural and semantic properties of code that can be extracted from code-views like the Control Flow Graph (CFG), Data Flow Graph (DFG), Abstract Syntax Tree (AST), etc. Unfortunately, the process of generating and integrating code-views for every programming language is cumbersome and time consuming. To overcome this barrier, we propose our tool COMEX - a framework that allows researchers and developers to create and combine multiple code-views which can be used by machine learning (ML) models for various SE tasks. Some salient features of our tool are: (i) it works directly on source code (which need not be compilable), (ii) it currently supports Java and C#, (iii) it can analyze both method-level snippets and program-level snippets by using both intra-procedural and inter-procedural analysis, and (iv) it is easily extendable to other languages as it is built on tree-sitter - a widely used incremental parser that supports over 40 languages. We believe this easy-to-use code-view generation and customization tool will give impetus to research in source code representation learning methods and ML4SE. Tool: https://pypi.org/project/comex - GitHub: https://github.com/IBM/tree-sitter-codeviews - Demo: https://youtu.be/GER6U87FVbU

cs.SE↗

arXiv2021

Modeling Live Video Streaming: Real-Time Classification, QoE Inference, and Field Evaluation

Social media, professional sports, and video games are driving rapid growth in live video streaming, on platforms such as Twitch and YouTube Live. Live streaming experience is very susceptible to short-time-scale network congestion since client playback buffers are often no more than a few seconds. Unfortunately, identifying such streams and measuring their QoE for network management is challenging, since content providers largely use the same delivery infrastructure for live and video-on-demand (VoD) streaming, and packet inspection techniques (including SNI/DNS query monitoring) cannot always distinguish between the two. In this paper, we design, build, and deploy ReCLive: a machine learning method for live video detection and QoE measurement based on network-level behavioral characteristics. Our contributions are four-fold: (1) We analyze about 23,000 video streams from Twitch and YouTube, and identify key features in their traffic profile that differentiate live and on-demand streaming. We release our traffic traces as open data to the public; (2) We develop an LSTM-based binary classifier model that distinguishes live from on-demand streams in real-time with over 95% accuracy across providers; (3) We develop a method that estimates QoE metrics of live streaming flows in terms of resolution and buffer stall events with overall accuracies of 93% and 90%, respectively; and (4) Finally, we prototype our solution, train it in the lab, and deploy it in a live ISP network serving more than 7,000 subscribers. Our method provides ISPs with fine-grained visibility into live video streams, enabling them to measure and improve user experience.

cs.NI↗

arXiv2021

Monolith to Microservices: Representing Application Software through Heterogeneous Graph Neural Network

Monolithic software encapsulates all functional capabilities into a single deployable unit. But managing it becomes harder as the demand for new functionalities grow. Microservice architecture is seen as an alternate as it advocates building an application through a set of loosely coupled small services wherein each service owns a single functional responsibility. But the challenges associated with the separation of functional modules, slows down the migration of a monolithic code into microservices. In this work, we propose a representation learning based solution to tackle this problem. We use a heterogeneous graph to jointly represent software artifacts (like programs and resources) and the different relationships they share (function calls, inheritance, etc.), and perform a constraint-based clustering through a novel heterogeneous graph neural network. Experimental studies show that our approach is effective on monoliths of different types.

cs.SE↗

arXiv2020

Adversarial Black-Box Attacks On Text Classifiers Using Multi-Objective Genetic Optimization Guided By Deep Networks

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic search with multi-objective optimization guided by deep learning based inferences and Seq2Seq mutation to generate semantically similar but imperceptible adversaries. We compare our approach with DeepWordBug (DWB) on SST and IMDB sentiment datasets by attacking three trained models viz. char-LSTM, word-LSTM and elmo-LSTM. On an average, we achieve an attack success rate of 65.67% for SST and 36.45% for IMDB across the three models showing an improvement of 49.48% and 101% respectively. Furthermore, our qualitative study indicates that 94% of the time, the users were not able to distinguish between an original and adversarial sample.

cs.AI↗