STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis

• URL: http://arxiv.org/abs/2406.10018v1
• Date: Fri, 14 Jun 2024 13:28:31 GMT
• Title: STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis
• Abstract summary: This work performs the first study on the static analysis integration in LLM-based repository-level code completion. We first implement a framework STALL+, which supports an extendable and customizable integration of multiple static analysis strategies. Our findings show that integrating file-level dependencies in prompting phase performs the best while the integration in post-processing phase performs the worse.
• Score: 8.059606338318538
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Repository-level code completion is challenging as it involves complicated contexts from multiple files in the repository. To date, researchers have proposed two technical categories to enhance LLM-based repository-level code completion, i.e., retrieval-augmented generation (RAG) and static analysis integration. This work performs the first study on the static analysis integration in LLM-based repository-level code completion by investigating both the effectiveness and efficiency of static analysis integration strategies across different phases of code completion. We first implement a framework STALL+, which supports an extendable and customizable integration of multiple static analysis strategies into the complete pipeline of LLM-based repository-level code completion; and based on STALL+, we perform extensive experiments by including different code LLMs on the latest repository-level code completion benchmark CrossCodeEval. Our findings show that integrating file-level dependencies in prompting phase performs the best while the integration in post-processing phase performs the worse. Additionally, we observe different improvements from static analysis between dynamic languages and static languages, i.e., the best combination is prompting-phase with decoding-phase integration for Java while the best combination is prompting-phase with post-processing-phase integration for Python given the limitations of statically analyzing dynamic languages. Additionally, we find the complementarity between RAG and static analysis integration as well as their cost-effectiveness after combination.

Related papers

• OpenCompass: A Universal Evaluation Platform for Large Language Models [62.59671563145442]
  General-purpose large language models (LLMs) have become a critical link in advancing technological development.<n>Mainstream benchmark datasets face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing.<n>This paper proposes and open-source Open LLMs, a one-stop, scalable, and high-concurrency general-purpose evaluation platform.
  arXiv  Detail & Related papers  (2026-05-19T02:50:11Z)
• Does Teaming-Up LLMs Improve Secure Code Generation? A Comprehensive Evaluation with Multi-LLMSecCodeEval [22.812621042022105]
  Multi-LLMSECCODEEVAL is a framework for assessing and enhancing security across the vulnerability management lifecycle.<n>We benchmark ten pipelines spanning single model, ensemble, collaborative, and hybrid designs.
  arXiv  Detail & Related papers  (2026-03-24T02:13:31Z)
• PymooLab: An Open-Source Visual Analytics Framework for Multi-Objective Optimization using LLM-Based Code Generation and MCDM [0.0]
  PymooLab is an open-source visual analytics environment built on top of textitpymoo.<n>It unifies configuration, execution monitoring, and formal decision support in a single reproducible workflow.<n>For computationally intensive studies, PymooLab relies on the native textitpymoo acceleration pathway through JAX.
  arXiv  Detail & Related papers  (2026-03-02T00:56:32Z)
• Enhancing LLM-Based Test Generation by Eliminating Covered Code [2.2566909388480743]
  Large Language Models (LLMs) have shown promise in improving test generation.<n>We propose a scalable LLM-based unit test generation method.<n>Our approach outperforms state-of-the-art LLM-based and search-based methods.
  arXiv  Detail & Related papers  (2026-02-25T15:16:43Z)
• AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion [55.21541958868449]
  We propose AlignCoder, a repository-level code completion framework.<n>Our framework generates an enhanced query that bridges the semantic gap between the initial query and the target code.<n>We employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval.
  arXiv  Detail & Related papers  (2026-01-27T15:23:14Z)
• AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito [0.0]
  This study develops an integrated AI framework to facilitate the transformation of legacy finite difference implementations into the Devito environment.<n>Retrieval-Augmented Generation (RAG) and open-source Large Language Models are combined through multi-stage iterative in the system's hybrid LangGraph architecture.
  arXiv  Detail & Related papers  (2026-01-26T11:31:00Z)
• Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation [3.9189409002585567]
  Large language models (LLMs) have demonstrated strong performance on function-level code generation benchmarks.<n>We introduce a benchmark derived from real-world open-source repositories to evaluate generalization under practical conditions.<n>We examine how input specification completeness and retrieval-augmented generation affect class-level correctness across multiple state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-10-30T04:30:23Z)
• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding [73.60257070465377]
  AdaVideoRAG is a novel framework that adapts retrieval based on query complexity using a lightweight intent classifier.<n>Our framework employs an Omni-Knowledge Indexing module to build hierarchical databases from text (captions, ASR, OCR), visual features, and semantic graphs.<n> Experiments demonstrate improved efficiency and accuracy for long-video understanding, with seamless integration into existing MLLMs.
  arXiv  Detail & Related papers  (2025-06-16T15:18:15Z)
• Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
  Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
  arXiv  Detail & Related papers  (2025-05-26T15:27:55Z)
• What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond [32.467437657603604]
  Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. We propose AllianceCoder, a novel context-integrated method that employs chain-of-thought prompting to decompose user queries into implementation steps and retrieves APIs via semantic description matching. Through extensive experiments on CoderEval and RepoExec, AllianceCoder achieves state-of-the-art performance, improving Pass@1 by up to 20% over existing approaches.
  arXiv  Detail & Related papers  (2025-03-26T14:41:38Z)
• Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting [86.15347226865826]
  We design a new end-to-end object-aware lifting approach, named Unified-Lift. We augment each Gaussian point with an additional Gaussian-level feature learned using a contrastive loss to encode instance information. We conduct experiments on three benchmarks: LERF-Masked, Replica, and Messy Rooms.
  arXiv  Detail & Related papers  (2025-03-18T08:42:23Z)
• LLM Test Generation via Iterative Hybrid Program Analysis [7.121002367542988]
  Panta is a technique that emulates the iterative process human developers follow when analyzing code and constructing test cases. Our empirical evaluation, conducted on classes with high cyclomatic complexity from open-source projects, demonstrates that Panta achieves 26% higher line coverage and 23% higher branch coverage.
  arXiv  Detail & Related papers  (2025-03-17T16:10:38Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis [53.38518232934096]
  Multi-task learning (MTL) is a powerful machine learning paradigm designed to leverage shared knowledge across tasks to improve generalization and performance. We propose an MTL approach at the intersection between task clustering and feature transformation based on a two-phase iterative aggregation of targets and features. In both phases, a key aspect is to preserve the interpretability of the reduced targets and features through the aggregation with the mean, which is motivated by applications to Earth science.
  arXiv  Detail & Related papers  (2024-06-12T08:30:16Z)
• Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository [4.767858874370881]
  We introduce RepoClassBench, a benchmark designed to rigorously evaluate LLMs in generating class-level code within real-world repositories. RepoClassBench includes "Natural Language to Class generation" tasks across Java, Python & C# from a selection of repositories. We introduce Retrieve-Repotools-Reflect (RRR), a novel approach that equips LLMs with static analysis tools to iteratively navigate & reason about repository-level context.
  arXiv  Detail & Related papers  (2024-04-22T03:52:54Z)
• Repoformer: Selective Retrieval for Repository-Level Code Completion [30.706277772743615]
  Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. In this paper, we propose a selective RAG framework to avoid retrieval when unnecessary. We show that our framework is able to accommodate different generation models, retrievers, and programming languages.
  arXiv  Detail & Related papers  (2024-03-15T06:59:43Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• Integrating Static Code Analysis Toolchains [0.8246494848934447]
  State of the art toolchains support features for either test execution and build automation or traceability between tests, requirements and design information. Our approach combines all those features and extends traceability to the source code level, incorporating static code analysis.
  arXiv  Detail & Related papers  (2024-03-09T18:59:50Z)
• PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion [96.47420221442397]
  We construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. We test 3 closed-source and 4 open-source LLMs using a benchmark that incorporates robustness settings. We find that GPT-4 exhibits the highest performance and strong robustness in our benchmark.
  arXiv  Detail & Related papers  (2024-03-06T15:33:32Z)
• Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context [41.91246546266515]
  We argue that Integrated Development Environments (IDEs) can provide direct, accurate and real-time cross-file information for repository-level code completion. We propose a framework that leveragesIDE native static contexts for cross-context construction and diagnosis results for self-refinement.
  arXiv  Detail & Related papers  (2024-02-06T01:59:41Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• Comparative Code Structure Analysis using Deep Learning for Performance Prediction [18.226950022938954]
  This paper aims to assess the feasibility of using purely static information (e.g., abstract syntax tree or AST) of applications to predict performance change based on the change in code structure. Our evaluations of several deep embedding learning methods demonstrate that tree-based Long Short-Term Memory (LSTM) models can leverage the hierarchical structure of source-code to discover latent representations and achieve up to 84% (individual problem) and 73% (combined dataset with multiple of problems) accuracy in predicting the change in performance.
  arXiv  Detail & Related papers  (2021-02-12T16:59:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.