arXiv subjects

Caihua Li

Publications and source records attributed to Caihua Li.

7 recordsLinked to original sources

arXiv2026

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as profoundly difficult for large language models, thereby significantly accelerating the evolution of autonomous coding agents. This paper presents a systematic survey of this emerging domain. We begin by examining data construction pipelines, covering automated collection and synthesis approaches. We then provide a comprehensive analysis of methodologies, spanning training-free frameworks with their modular components to training-based techniques, including supervised fine-tuning and reinforcement learning. Subsequently, we discuss critical analyses of data quality and agent behavior, alongside practical applications. Finally, we identify key challenges and outline promising directions for future research. An open-source repository is maintained at https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution to serve as a dynamic resource in this field.

cs.SE↗

arXiv2026

SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the existing GitHub issue resolution data construction pipeline is challenging and labor-intensive. We identify three key limitations in existing pipelines: (1) test patches collected often omit binary file changes; (2) the manual construction of evaluation environments is labor-intensive; and (3) the fail2pass validation phase requires manual inspection of test logs and writing custom parsing code to extract test status from logs. In this paper, we propose SWE-Factory, a fully automated issue resolution data construction pipeline, to resolve these limitations. First, our pipeline automatically recovers missing binary test files and ensures the correctness of test patches. Second, we introduce SWE-Builder, a LLM-based multi-agent system that automates evaluation environment construction. Third, we introduce a standardized, exit-code-based log parsing method to automatically extract test status, enabling a fully automated fail2pass validation. Experiments on 671 real-world GitHub issues across four programming languages show that our method can effectively construct valid evaluation environments for GitHub issues at a reasonable cost. For example, with GPT-4.1 mini, our SWE-Builder constructs 337 valid task instances out of 671 issues, at $0.047 per instance. Our ablation study further shows the effectiveness of different components of SWE-Builder. We also demonstrate through manual inspection that our exit-code-based fail2pass validation method is highly accurate, achieving an F1 score of 0.99. Additionally, we conduct an exploratory experiment to investigate whether we can use SWE-Factory to enhance models' software engineering ability.

cs.SE↗

arXiv2025

Confidential Prompting: Privacy-preserving LLM Inference on Cloud

This paper introduces a vision of confidential prompting: securing user prompts from an untrusted, cloud-hosted large language model (LLM) while preserving model confidentiality, output invariance, and compute efficiency. As a first step toward this vision, we present Petridish, a system built on top of confidential computing and its core contribution, a novel technology called Secure Partitioned Decoding (SPD). Petridish runs the LLM service inside a confidential virtual machine (CVM), which protects the secrets, i.e., the LLM parameters and user prompts, from adversaries outside the CVM. Importantly, it splits the LLM service for a user into two processes, using SPD: a per-user process performs prefill with the user prompts and computes attention scores during decoding; a service process, shared by all users, batches the attention scores from per-user processes and generates output tokens for all users. Both the LLM provider and the users trust Petridish's CVM and its operating system, which guarantees isolation between processes and limits their outbound network capabilities to control information flow. The CVM's attestation capability and its open-source software stack enable Petridish to provide auditable protection of both user prompt and LLM confidentiality. Together, Petridish maintains full utility of LLM service and enables practical, privacy-preserving cloud-hosted LLM inference for sensitive applications, such as processing personal data, clinical records, and financial documents.

cs.CR↗

arXiv2025

MappedTrace: Tracing Pointer Remotely with Compiler-generated Maps

Existing precise pointer tracing methods introduce substantial runtime overhead to the program being traced and are applicable only at specific program execution points. We propose MappedTrace that leverages compiler-generated read-only maps to accurately identify all pointers in any given snapshot of a program's execution state. The maps record the locations and types of pointers, allowing the tracer to precisely identify pointers without requiring the traced program to maintain bookkeeping data structures or poll at safe points, thereby reducing runtime overhead. By running the tracer from a different address space or machine, MappedTrace presents new opportunities to improve memory management techniques like memory leak detection and enables novel use cases such as infinite memory abstraction for resource-constrained environments.

cs.PL↗

arXiv2024

Blindfold: Confidential Memory Management by Untrusted Operating System

Confidential Computing (CC) has received increasing attention in recent years as a mechanism to protect user data from untrusted operating systems (OSes). Existing CC solutions hide confidential memory from the OS and/or encrypt it to achieve confidentiality. In doing so, they render OS memory optimization unusable or complicate the trusted computing base (TCB) required for optimization. This paper presents our results toward overcoming these limitations, synthesized in a CC design named Blindfold. Like many other CC solutions, Blindfold relies on a small trusted software component running at a higher privilege level than the kernel, called Guardian. It features three techniques that can enhance existing CC solutions. First, instead of nesting page tables, Guardian mediates how the OS accesses memory and handles exceptions by switching page and interrupt tables. Second, Blindfold employs a lightweight capability system to regulate the kernel semantic access to user memory, unifying case-by-case approaches in previous work. Finally, Blindfold provides carefully designed secure ABI for confidential memory management without encryption. We report an implementation of Blindfold that works on ARMv8-A/Linux. Using Blindfold prototype, we are able to evaluate the cost of enabling confidential memory management by the untrusted Linux kernel. We show Blindfold has a smaller runtime TCB than related systems and enjoys competitive performance. More importantly, we show that the Linux kernel, including all of its memory optimizations except memory compression, can function properly for confidential memory. This requires only about 400 lines of kernel modifications.

cs.CR↗

arXiv2022

MProtect: Operating System Memory Management without Access

Modern operating systems (OSes) have unfettered access to application data, assuming that applications trust them. This assumption, however, is problematic under many scenarios where either the OS provider is not trustworthy or the OS can be compromised due to its large attack surface. Our investigation began with the hypothesis that unfettered access to memory is not fundamentally necessary for the OS to perform its own job, including managing the memory. The result is a system called MProtect that leverages a small piece of software running at a higher privilege level than the OS. MProtect protects the entire user space of a process, requires only a small modification to the OS, and supports major architectures such as ARM, x86 and RISC-V. Unlike prior works that resorted to nested virtualization, which is often undesirable in mobile and embedded systems, MProtect mediates how the OS accesses the memory and handles exceptions. We report an implementation of MProtect called MGuard with ARMv8/Linux and evaluate its performance with both macro and microbenchmarks. We show MGuard has a runtime TCB 2~3 times smaller than related systems and enjoys competitive performance while supporting legitimate OS access to the user space.

cs.OS↗

arXiv2017

Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation

Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to the same meaning, namely pseudo multi-sense. In this paper, we introduce the concept of pseudo multi-sense, and then propose an algorithm to detect such cases. With the consideration of the detected pseudo multi-sense cases, we try to refine the existing word embeddings to eliminate the influence of pseudo multi-sense. Moreover, we apply our algorithm on previous released multi-sense word embeddings and tested it on artificial word similarity tasks and the analogy task. The result of the experiments shows that diminishing pseudo multi-sense can improve the quality of word representations. Thus, our method is actually an efficient way to reduce linguistic complexity.

cs.CL↗