Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation

• URL: http://arxiv.org/abs/2401.06391v3
• Date: Thu, 18 Jul 2024 07:04:38 GMT
• Title: Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
• Abstract summary: Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies. We introduce ToolGen, an approach that integrates autocompletion tools into the code LLM generation process to address these dependencies. ToolGen comprises two main phases: Trigger Insertion and Model Fine-tuning (Offline), and Tool-integrated Code Generation (Online)
• Score: 15.461189659020187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attributes), resulting in dependency errors such as undefined-variable and no-member errors. In this work, we introduce ToolGen, an approach that integrates autocompletion tools into the code LLM generation process to address these dependencies. ToolGen comprises two main phases: Trigger Insertion and Model Fine-tuning (Offline), and Tool-integrated Code Generation (Online). During the offline phase, ToolGen augments functions within a given code corpus with a special mark token, indicating positions to trigger autocompletion tools. These augmented functions, along with their corresponding docstrings, are then used to fine-tune a selected code LLM. In the online phase, ToolGen iteratively generates functions by predicting tokens step-by-step using the fine-tuned LLM. Whenever a mark token is encountered, ToolGen invokes the autocompletion tool to suggest code completions and selects the most appropriate one. We conduct comprehensive experiments to evaluate ToolGen's effectiveness in repository-level code generation. To facilitate this evaluation, we create a benchmark comprising 671 real-world code repositories and introduce two new dependency-based metrics: Dependency Coverage and Static Validity Rate. The results demonstrate that ToolGen significantly improves Dependency Coverage by 31.4% to 39.1% and Static Validity Rate by 44.9% to 57.7% across the three LLMs, while maintaining competitive or improved performance in widely recognized similarity metrics such as BLEU-4, CodeBLEU, Edit Similarity, and Exact Match. On the CoderEval dataset, ToolGen achieves improvements of 40.0% and 25.0% in Pass@1 for CodeT5 and CodeLlama, respectively.

Related papers

• Functional and Secure Code Generation with Task Vectors [7.757776817999749]
  Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities.<n>We develop a novel method, SecVecCoder, leveraging task vectors to produce trustworthy code that is simultaneously functional and secure.
  arXiv  Detail & Related papers  (2026-07-08T19:32:22Z)
• Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning [82.89535601592739]
  We propose a two-stage pipeline that generates reliable base tool-use trajectories through self-evolving synthesis with multi-level validation.<n>These augmentations introduce distractor tools, indirect or ambiguous user queries, and noisy, multi-format, or erroneous tool outputs.<n>This design enables automatic reward computation via reference matching for standard cases and lightweight judge-assisted verification for special behaviors such as error detection.
  arXiv  Detail & Related papers  (2026-04-10T18:38:52Z)
• Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios [13.708123854369303]
  CLI-Tool-Bench is a structure-agnostic benchmark for evaluating the ground-up generation of Command-Line Interface tools.<n>It features 100 diverse real-world repositories evaluated via a black-box differential testing framework.<n>Agent-generated software is executed in sandboxes, comparing system side effects and terminal outputs against human-written oracles.
  arXiv  Detail & Related papers  (2026-04-08T07:09:10Z)
• EvolveTool-Bench: Evaluating the Quality of LLM-Generated Tool Libraries as Software Artifacts [0.0]
  We introduce EvolveToolBench, a diagnostic benchmark for tool libraries in software engineering.<n>We define library-level software quality metrics -- reuse, redundancy, composition success, regression, and safety.<n>We show that systems with similar task completion differ by up to 18% in library health, revealing software quality risks invisible to task-only evaluation.
  arXiv  Detail & Related papers  (2026-04-01T02:21:55Z)
• ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization [51.92237664440418]
  ToolRosetta is a framework that automatically translates open-source code repositories and APIs into MCP-compatible tools.<n>Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant toolchains, and converts them into executable MCP services.
  arXiv  Detail & Related papers  (2026-03-10T07:19:43Z)
• Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls [56.407063247662336]
  We introduce Gecko, a comprehensive environment that simulates tool responses using a combination of rules and LLMs.<n>GATS consistently improves the tool calling performance of various LLMs including GPT-4o, GPT-5, and Gemini-3.0-pro.
  arXiv  Detail & Related papers  (2026-02-22T15:02:00Z)
• Evaluating and Achieving Controllable Code Completion in Code LLM [89.64782747840225]
  We present the first instruction-guided code completion benchmark, Controllable Code Completion Benchmark (C3-Bench)<n>We reveal substantial gaps in instruction-following capabilities between open-source and advanced proprietary models during code completion tasks.<n>The resulting model, Qwen2.5-Coder-C3, achieves state-of-the-art performance on C3-Bench.
  arXiv  Detail & Related papers  (2026-01-22T11:40:04Z)
• Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback [1.1017250479834206]
  Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors.<n>We propose a retrieval-augmented, multi-tool repair workflow in which a single code-generating LLM iteratively refines its outputs.
  arXiv  Detail & Related papers  (2026-01-01T23:34:00Z)
• AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning [79.65732142949014]
  Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories.<n>Existing approaches assume a fixed inventory of tools, limiting LLM agents' adaptability to new or evolving toolsets.<n>We present AutoTool, a framework that equips LLM agents with dynamic tool-selection capabilities throughout their reasoning trajectories.
  arXiv  Detail & Related papers  (2025-12-15T12:38:04Z)
• RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use [50.52940111891476]
  Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools.<n>We present RLFactory, a plug-and-play reinforcement learning framework for multi-round tool use.
  arXiv  Detail & Related papers  (2025-08-31T16:47:31Z)
• ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients" [53.7887350405379]
  Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like DFS.<n>We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients"<n>This "answer-first" approach led to ToolGrad-5k, a dataset generated with more complex tool use, lower cost, and 100% pass rate.
  arXiv  Detail & Related papers  (2025-08-06T05:04:00Z)
• Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach [6.289275189295223]
  We investigate the relationship between code complexity and the success of Large Language Models generated code.<n>We propose an iterative feedback method, where LLMs are prompted to generate correct code based on complexity metrics from previous failed outputs.<n>Experiment results show that our approach makes notable improvements, particularly with a smaller LLM.
  arXiv  Detail & Related papers  (2025-05-29T19:06:14Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models [49.04652315815501]
  Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task.
  arXiv  Detail & Related papers  (2025-02-17T03:42:28Z)
• SnipGen: A Mining Repository Framework for Evaluating LLMs for Code [51.07471575337676]
  Language Models (LLMs) are trained on extensive datasets that include code repositories. evaluating their effectiveness poses significant challenges due to the potential overlap between the datasets used for training and those employed for evaluation. We introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering across various downstream tasks for code generation.
  arXiv  Detail & Related papers  (2025-02-10T21:28:15Z)
• ToolGen: Unified Tool Retrieval and Calling via Generation [34.34787641393914]
  We introduce ToolGen, a paradigm shift that integrates tool knowledge directly into the large language models' parameters. We show that ToolGen achieves superior results in both tool retrieval and autonomous task completion. ToolGen paves the way for more versatile, efficient, and autonomous AI systems.
  arXiv  Detail & Related papers  (2024-10-04T13:52:32Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data [60.75578581719921]
  Large language models (LLMs) have shown great potential for automatic code generation. Recent studies highlight that many LLM-generated code contains serious security vulnerabilities. We introduce HexaCoder, a novel approach to enhance the ability of LLMs to generate secure codes.
  arXiv  Detail & Related papers  (2024-09-10T12:01:43Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present textbfmethodnamews, a novel benchmark designed to evaluate repository-level code generation. We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• 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)
• Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback [29.136378191436396]
  We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project's context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository.
  arXiv  Detail & Related papers  (2024-03-25T14:07:27Z)
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error [54.954211216847135]
  Existing large language models (LLMs) only reach a correctness rate in the range of 30% to 60%. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE) STE orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
  arXiv  Detail & Related papers  (2024-03-07T18:50:51Z)
• 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)
• CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges [41.038584732889895]
  Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks. Our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We present CodeAgent, a novel LLM-based agent framework that employs external tools for effective repo-level code generation.
  arXiv  Detail & Related papers  (2024-01-14T18:12:03Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [75.64181719386497]
  We present CRAFT, a tool creation and retrieval framework for large language models (LLMs) It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
  arXiv  Detail & Related papers  (2023-09-29T17:40:26Z)

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.