Large language models (LLMs) have significantly advanced autonomous software engineering, leading to a growing number of software engineering agents that assist developers in automatic program repair. Issue localization forms the basis for accurate patch generation. However, because of limitations caused by the context window length of LLMs, existing issue localization methods face challenges in balancing concise yet effective contexts and adequately comprehensive search spaces. In this paper, we introduce CoSIL, an LLM driven, simple yet powerful function level issue localization method without training or indexing. CoSIL reduces the search space through module call graphs, iteratively searches the function call graph to obtain relevant contexts, and uses context pruning to control the search direction and manage contexts effectively. Importantly, the call graph is dynamically constructed by the LLM during search, eliminating the need for pre-parsing. Experiment results demonstrate that CoSIL achieves a Top-1 localization success rate of 43 percent and 44.6 percent on SWE bench Lite and SWE bench Verified, respectively, using Qwen2.5 Coder 32B, outperforming existing methods by 8.6 to 98.2 percent. When CoSIL is applied to guide the patch generation stage, the resolved rate further improves by 9.3 to 31.5 percent.
Automated Program Repair (APR) is a task to automatically generate patches for the buggy code. However, most research focuses on generating correct patches while ignoring the consistency between the fixed code and the original buggy code. How to conduct adaptive bug fixing and generate patches with minimal modifications have seldom been investigated. To bridge this gap, we first introduce a novel task, namely AdaPR (Adaptive Program Repair). We then propose a two-stage approach AdaPatcher (Adaptive Patch Generator) to enhance program repair while maintaining the consistency. In the first stage, we utilize a Bug Locator with self-debug learning to accurately pinpoint bug locations. In the second stage, we train a Program Modifier to ensure consistency between the post-modified fixed code and the pre-modified buggy code. The Program Modifier is enhanced with a location-aware repair learning strategy to generate patches based on identified buggy lines, a hybrid training strategy for selective reference and an adaptive preference learning to prioritize fewer changes. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our two-stage framework for the newly proposed AdaPR task.
The irruption of DeepSeek-R1 constitutes a turning point for the AI industry in general and the LLMs in particular. Its capabilities have demonstrated outstanding performance in several tasks, including creative thinking, code generation, maths and automated program repair, at apparently lower execution cost. However, LLMs must adhere to an important qualitative property, i.e., their alignment with safety and human values. A clear competitor of DeepSeek-R1 is its American counterpart, OpenAI's o3-mini model, which is expected to set high standards in terms of performance, safety and cost. In this technical report, we systematically assess the safety level of both DeepSeek-R1 (70b version) and OpenAI's o3-mini (beta version). To this end, we make use of our recently released automated safety testing tool, named ASTRAL. By leveraging this tool, we automatically and systematically generated and executed 1,260 test inputs on both models. After conducting a semi-automated assessment of the outcomes provided by both LLMs, the results indicate that DeepSeek-R1 produces significantly more unsafe responses (12%) than OpenAI's o3-mini (1.2%).
LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most of LLM-based APR methods rely on a single type of software information, without fully leveraging different software artifacts. Despite this, many LLM-based approaches do not explore which specific types of information best assist in APR. Addressing this gap is crucial for advancing LLM-based APR techniques. We propose DEVLoRe to use issue content (description and message) and stack error traces to localize buggy methods, then rely on debug information in buggy methods and issue content and stack error to localize buggy lines and generate plausible patches which can pass all unit tests. The results show that while issue content is particularly effective in assisting LLMs with fault localization and program repair, different types of software artifacts complement each other. By incorporating different artifacts, DEVLoRe successfully locates 49.3% and 47.6% of single and non-single buggy methods and generates 56.0% and 14.5% plausible patches for the Defects4J v2.0 dataset, respectively. This outperforms current state-of-the-art APR methods. Furthermore, we re-implemented and evaluated our framework, demonstrating its effectiveness in its effectiveness in resolving 9 unique issues compared to other state-of-the-art frameworks using the same or more advanced models on SWE-bench Lite.We also discussed whether a leading framework for Python code can be directly applied to Java code, or vice versa. The source code and experimental results of this work for replication are available at https://github.com/XYZboom/DEVLoRe.
The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in LLMs. However, these methods suffer from LLMs' inefficiency and limited reasoning capacity. In this work, we propose an LLM programming workflow (LPW) designed to improve both initial code generation and subsequent refinements within a structured two-phase workflow. Specifically, the solution generation phase formulates a solution plan, which is then verified through visible tests to specify the intended natural language solution. Subsequently, the code implementation phase drafts an initial code according to the solution plan and its verification. If the generated code fails the visible tests, the plan verification serves as the intended solution to consistently inform the refinement process for correcting bugs. Compared to state-of-the-art methods across various existing LLMs, LPW significantly improves the Pass@1 accuracy by up to 16.4% on well-established text-to-code generation benchmarks. LPW also sets new state-of-the-art Pass@1 accuracy, achieving 98.2% on HumanEval, 84.8% on MBPP, 59.3% on LiveCode, 62.6% on APPS, and 34.7% on CodeContest, using GPT-4o as the backbone. Our code is publicly available at: https://github.com/you68681/lpw
While large language models have made significant strides in code generation, the pass rate of the generated code is bottlenecked on subtle errors, often requiring human intervention to pass tests, especially for complex problems. Existing LLM-based debugging systems treat generated programs as monolithic units, failing to address bugs at multiple levels of granularity, from low-level syntax errors to high-level algorithmic flaws. In this paper, we introduce Multi-Granularity Debugger (MGDebugger), a hierarchical code debugger by isolating, identifying, and resolving bugs at various levels of granularity. MGDebugger decomposes problematic code into a hierarchical tree structure of subfunctions, with each level representing a particular granularity of error. During debugging, it analyzes each subfunction and iteratively resolves bugs in a bottom-up manner. To effectively test each subfunction, we propose an LLM-simulated Python executor, which traces code execution and tracks important variable states to pinpoint errors accurately. Extensive experiments demonstrate that MGDebugger outperforms existing debugging systems, achieving an 18.9% improvement in accuracy over seed generations in HumanEval and a 97.6% repair success rate in HumanEvalFix. Furthermore, MGDebugger effectively fixes bugs across different categories and difficulty levels, demonstrating its robustness and effectiveness.
AI-driven program repair uses AI models to repair buggy software by producing patches. Rapid advancements in AI surely impact state-of-the-art performance of program repair. Yet, grasping this progress requires frequent and standardized evaluations. We propose RepairBench, a novel leaderboard for AI-driven program repair. The key characteristics of RepairBench are: 1) it is execution-based: all patches are compiled and executed against a test suite, 2) it assesses frontier models in a frequent and standardized way. RepairBench leverages two high-quality benchmarks, Defects4J and GitBug-Java, to evaluate frontier models against real-world program repair tasks. We publicly release the evaluation framework of RepairBench. We will update the leaderboard as new frontier models are released.
Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines.
LLMs have long demonstrated remarkable effectiveness in automatic program repair (APR), with OpenAI's ChatGPT being one of the most widely used models in this domain. Through continuous iterations and upgrades of GPT-family models, their performance in fixing bugs has already reached state-of-the-art levels. However, there are few works comparing the effectiveness and variations of different versions of GPT-family models on APR. In this work, inspired by the recent public release of the GPT-o1 models, we conduct the first study to compare the effectiveness of different versions of the GPT-family models in APR. We evaluate the performance of the latest version of the GPT-family models (i.e., O1-preview and O1-mini), GPT-4o, and the historical version of ChatGPT on APR. We conduct an empirical study of the four GPT-family models against other LLMs and APR techniques on the QuixBugs benchmark from multiple evaluation perspectives, including repair success rate, repair cost, response length, and behavior patterns. The results demonstrate that O1's repair capability exceeds that of prior GPT-family models, successfully fixing all 40 bugs in the benchmark. Our work can serve as a foundation for further in-depth exploration of the applications of GPT-family models in APR.
The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering program reliability while simultaneously diminishing the financial burden of manual repairs. Commercial-scale language models (LM) have taken APR to unprecedented levels. However, the emergence reveals that for models fewer than 100B parameters, making single-step modifications may be difficult to achieve the desired effect. Moreover, humans interact with the LM through explicit prompts, which hinders the LM from receiving feedback from compiler and test cases to automatically optimize its repair policies. In this literature, we explore how small-scale LM (less than 20B) achieve excellent performance through process supervision and feedback. We start by constructing a dataset named CodeNet4Repair, replete with multiple repair records, which supervises the fine-tuning of a foundational model. Building upon the encouraging outcomes of reinforcement learning, we develop a reward model that serves as a critic, providing feedback for the fine-tuned LM's action, progressively optimizing its policy. During inference, we require the LM to generate solutions iteratively until the repair effect no longer improves or hits the maximum step limit. The results show that process-based not only outperforms larger outcome-based generation methods, but also nearly matches the performance of closed-source commercial large-scale LMs.
Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry practitioners have developed various autonomous LLM agents to perform end-to-end software development tasks. These agents are equipped with the ability to use tools, run commands, observe feedback from the environment, and plan for future actions. However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents? To attempt to answer this question, we build Agentless -- an agentless approach to automatically solve software development problems. Compared to the verbose and complex setup of agent-based approaches, Agentless employs a simplistic three-phase process of localization, repair, and patch validation, without letting the LLM decide future actions or operate with complex tools. Our results on the popular SWE-bench Lite benchmark show that surprisingly the simplistic Agentless is able to achieve both the highest performance (32.00%, 96 correct fixes) and low cost ($0.70) compared with all existing open-source software agents! Furthermore, we manually classified the problems in SWE-bench Lite and found problems with exact ground truth patch or insufficient/misleading issue descriptions. As such, we construct SWE-bench Lite-S by excluding such problematic issues to perform more rigorous evaluation and comparison. Our work highlights the current overlooked potential of a simple, interpretable technique in autonomous software development. We hope Agentless will help reset the baseline, starting point, and horizon for autonomous software agents, and inspire future work along this crucial direction.
Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text data and the need for semantic understanding for complex tasks like debugging and program repair. We introduce a novel strategy, monologue reasoning, to train Code LLMs to reason comprehensive semantics, encompassing high-level functional descriptions, local execution effects of individual statements, and overall input/output behavior, thereby linking static code text with dynamic execution states. We begin by collecting PyX, a clean Python corpus of fully executable code samples with functional descriptions and test cases. We propose training Code LLMs not only to write code but also to understand code semantics by reasoning about key properties, constraints, and execution behaviors using natural language, mimicking human verbal debugging, i.e., rubber-duck debugging. This approach led to the development of SemCoder, a Code LLM with only 6.7B parameters, which shows competitive performance with GPT-3.5-turbo on code generation and execution reasoning tasks. SemCoder achieves 79.3% on HumanEval (GPT-3.5-turbo: 76.8%), 63.6% on CRUXEval-I (GPT-3.5-turbo: 50.3%), and 63.9% on CRUXEval-O (GPT-3.5-turbo: 59.0%). We also study the effectiveness of SemCoder's monologue-style execution reasoning compared to concrete scratchpad reasoning, showing that our approach integrates semantics from multiple dimensions more smoothly. Finally, we demonstrate the potential of applying learned semantics to improve Code LLMs' debugging and self-refining capabilities. Our data, code, and models are available at: https://github.com/ARiSE-Lab/SemCoder.
The emergence of large language models (LLMs) has sparked enormous interest due to their potential application across a range of educational tasks. For example, recent work in programming education has used LLMs to generate learning resources, improve error messages, and provide feedback on code. However, one factor that limits progress within the field is that much of the research uses bespoke datasets and different evaluation metrics, making direct comparisons between results unreliable. Thus, there is a pressing need for standardization and benchmarks that facilitate the equitable comparison of competing approaches. One task where LLMs show great promise is program repair, which can be used to provide debugging support and next-step hints to students. In this article, we propose a novel educational program repair benchmark. We curate two high-quality publicly available programming datasets, present a unified evaluation procedure introducing a novel evaluation metric rouge@k for approximating the quality of repairs, and evaluate a set of five recent models to establish baseline performance.
Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of current infilling-style methods, which impedes LLMs from fully leveraging pre-trained knowledge for program repair. In addition, while some LLMs can locate and repair bugs in certain functions using the related artifacts (e.g., test cases), existing methods still depend on statement-level fault localization methods to provide a list of buggy hunks for repair. This restriction hinders LLMs from exploring potential patches beyond the given locations. In this paper, we investigate a new approach to adapt LLMs to program repair. Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective and allowing them to refine the whole program without first identifying faulty statements. Based on this insight, we designed D4C, a straightforward prompting framework for APR. D4C can repair 180 bugs correctly in Defects4J, with each patch being sampled only 10 times. This surpasses the SOTA APR methods with perfect fault localization by 10% and reduces the patch sampling number by 90%. Our findings reveal that (1) objective alignment is crucial for fully exploiting LLM's pre-trained capability, and (2) replacing the traditional localize-buggy-hunks-then-repair workflow with direct debugging is more effective for LLM-based APR methods. Thus, we believe this paper introduces a new mindset for harnessing LLMs in APR.
Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding. Nevertheless, software engineering involves the process of program improvement apart from coding, specifically to enable software maintenance (e.g. bug fixing) and software evolution (e.g. feature additions). In this paper, we propose an automated approach for solving GitHub issues to autonomously achieve program improvement. In our approach called AutoCodeRover, LLMs are combined with sophisticated code search capabilities, ultimately leading to a program modification or patch. In contrast to recent LLM agent approaches from AI researchers and practitioners, our outlook is more software engineering oriented. We work on a program representation (abstract syntax tree) as opposed to viewing a software project as a mere collection of files. Our code search exploits the program structure in the form of classes/methods to enhance LLM's understanding of the issue's root cause, and effectively retrieve a context via iterative search. The use of spectrum-based fault localization using tests, further sharpens the context, as long as a test-suite is available. Experiments on SWE-bench-lite (300 real-life GitHub issues) show increased efficacy in solving GitHub issues (19% on SWE-bench-lite), which is higher than the efficacy of the recently reported SWE-agent. In addition, AutoCodeRover achieved this efficacy with significantly lower cost (on average, $0.43 USD), compared to other baselines. We posit that our workflow enables autonomous software engineering, where, in future, auto-generated code from LLMs can be autonomously improved.
Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces RepairAgent, the first work to address the program repair challenge through an autonomous agent based on a large language model (LLM). Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools. RepairAgent freely interleaves gathering information about the bug, gathering repair ingredients, and validating fixes, while deciding which tools to invoke based on the gathered information and feedback from previous fix attempts. Key contributions that enable RepairAgent include a set of tools that are useful for program repair, a dynamically updated prompt format that allows the LLM to interact with these tools, and a finite state machine that guides the agent in invoking the tools. Our evaluation on the popular Defects4J dataset demonstrates RepairAgent's effectiveness in autonomously repairing 164 bugs, including 39 bugs not fixed by prior techniques. Interacting with the LLM imposes an average cost of 270,000 tokens per bug, which, under the current pricing of OpenAI's GPT-3.5 model, translates to 14 cents of USD per bug. To the best of our knowledge, this work is the first to present an autonomous, LLM-based agent for program repair, paving the way for future agent-based techniques in software engineering.
In this paper, we propose shifting the focus of robustness evaluation for Neural Program Repair (NPR) techniques toward naturally-occurring data transformations. To accomplish this, we first examine the naturalness of semantic-preserving transformations through a two-stage human study. This study includes (1) interviews with senior software developers to establish concrete criteria for evaluating the naturalness of these transformations, and (2) a survey involving 10 developers to assess the naturalness of 1,178 transformations, i.e., pairs of original and transformed programs, applied to 225 real-world bugs. Our findings show that only 60% of these transformations are deemed natural, while 20% are considered unnatural, with strong agreement among annotators. Moreover, the unnaturalness of these transformations significantly impacts both their applicability to benchmarks and the conclusions drawn from robustness testing. Next, we conduct natural robustness testing on NPR techniques to assess their true effectiveness against real-world data variations. Our experimental results reveal a substantial number of prediction changes in NPR techniques, leading to significant reductions in both plausible and correct patch rates when comparing performance on the original and transformed datasets. Additionally, we observe notable differences in performance improvements between NPR techniques, suggesting potential biases on NPR evaluation introduced by limited datasets. Finally, we propose an LLM-based metric to automate the assessment of transformation naturalness, ensuring the scalability of natural robustness testing.
Research shows that grammatical mistakes in a sentence can be corrected by translating it to another language and back using neural machine translation with language models. We investigate whether this correction capability of Large Language Models (LLMs) extends to Automatic Program Repair (APR). Current generative models for APR are pre-trained on source code and fine-tuned for repair. This paper proposes bypassing the fine-tuning step and using Round-Trip Translation (RTT): translation of code from one programming language to another programming or natural language, and back. We hypothesize that RTT with LLMs restores the most commonly seen patterns in code during pre-training, i.e., performs a regression toward the mean, which removes bugs as they are a form of noise w.r.t. the more frequent, natural, bug-free code in the training data. To test this hypothesis, we employ eight recent LLMs pre-trained on code, including the latest GPT versions, and four common program repair benchmarks in Java. We find that RTT with English as an intermediate language repaired 101 of 164 bugs with GPT-4 on the HumanEval-Java dataset. Moreover, 46 of these are unique bugs that are not repaired by other LLMs fine-tuned for APR. Our findings highlight the viability of round-trip translation with LLMs as a technique for automated program repair and its potential for research in software engineering. Keywords: automated program repair, large language model, machine translation
Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with many dimensions which have not been explored. Existing work mostly fine-tune LLMs with naive code representations and does not scale to frontier models. To address this problem, we propose RepairLLaMA, a novel program repair approach that 1) identifies optimal code representations for APR with fine-tuned models, and 2) pioneers state-of-the-art parameter-efficient fine-tuning technique (PEFT) for program repair. This results in RepairLLaMA producing a highly effective `program repair adapter' for fixing bugs with AI. Our experiments demonstrate the validity of both concepts. First, fine-tuning adapters with program repair specific code representations enables the model to use meaningful repair signals and produce better patches. Second, parameter-efficient fine-tuning helps fine-tuning to converge and clearly contributes to the effectiveness of RepairLLaMA in fixing bugs outside the fine-tuning data distribution. Overall, RepairLLaMA correctly fixes 144 Defects4J v2, 109 HumanEval-Java, and 20 GitBug-Java bugs, outperforming all baselines.
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization. Despite their promise, researchers must still be careful as numerous intricate factors can influence the outcomes of experiments involving LLMs. This paper initiates an open discussion on potential threats to the validity of LLM-based research including issues such as closed-source models, possible data leakage between LLM training data and research evaluation, and the reproducibility of LLM-based findings. In response, this paper proposes a set of guidelines tailored for SE researchers and Language Model (LM) providers to mitigate these concerns. The implications of the guidelines are illustrated using existing good practices followed by LLM providers and a practical example for SE researchers in the context of test case generation.