Current approaches to automated code generation often rely on monolithic models that lack real-time adaptability and scalability. This limitation is particularly evident in complex programming tasks that require dynamic adjustment and efficiency. The integration of neuroscience principles into Natural Language Processing (NLP) has the potential to revolutionize automated code generation. This paper presents CortexCompile, a novel modular system inspired by the specialized functions of the human brain's cortical regions. By emulating the distinct roles of the Prefrontal Cortex, Parietal Cortex, Temporal Lobe, and Motor Cortex, CortexCompile achieves significant advancements in scalability, efficiency, and adaptability compared to traditional monolithic models like GPT-4o. The system's architecture features a Task Orchestration Agent that manages dynamic task delegation and parallel processing, facilitating the generation of highly accurate and optimized code across increasingly complex programming tasks. Experimental evaluations demonstrate that CortexCompile consistently outperforms GPT-4o in development time, accuracy, and user satisfaction, particularly in tasks involving real-time strategy games and first-person shooters. These findings underscore the viability of neuroscience-inspired architectures in addressing the limitations of current NLP models, paving the way for more efficient and human-like AI systems.
Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate structurally redundant code, resulting in inefficiencies and reduced readability. To address this, we conduct the first empirical study to investigate the prevalence and nature of repetition across 19 state-of-the-art code LLMs using three widely-used benchmarks. Our study includes both quantitative and qualitative analyses, revealing that repetition is pervasive and manifests at various granularities and extents, including character, statement, and block levels. We further summarize a taxonomy of 20 repetition patterns. Building on our findings, we propose DeRep, a rule-based technique designed to detect and mitigate repetition in generated code. We evaluate DeRep using both open-source benchmarks and in an industrial setting. Our results demonstrate that DeRep significantly outperforms baselines in reducing repetition (with an average improvements of 91.3%, 93.5%, and 79.9% in rep-3, rep-line, and sim-line metrics) and enhancing code quality (with a Pass@1 increase of 208.3% over greedy search). Furthermore, integrating DeRep improves the performance of existing repetition mitigation methods, with Pass@1 improvements ranging from 53.7% to 215.7%.
Large Language Models (LLMs) have shown remarkable performance in automated code generation. However, existing approaches often rely heavily on pre-defined test cases, which become impractical in scenarios where such cases are unavailable. While prior works explore filtering techniques between programs and test cases, they overlook the refinement of test cases. To address this limitation, we introduce CoCoEvo, a novel LLM-based co-evolution framework that simultaneously evolves programs and test cases. CoCoEvo eliminates the dependency on pre-defined test cases by generating both programs and test cases directly from natural language problem descriptions and function headers. The framework employs specialized evolutionary operators, including LLM-based crossover and mutation operators for program evolution, along with a test case generation operator for test case evolution. Additionally, we propose optimization strategies such as a crossover rate scheduler to balance exploration and convergence, and a multi-objective optimization method for test case selection. Experimental results on multiple state-of-the-art LLMs demonstrate that CoCoEvo surpasses existing methods, achieving state-of-the-art performance in automated code generation and testing. These results underscore the potential of co-evolutionary techniques in advancing the field of automated programming.
This paper introduces SGCode, a flexible prompt-optimizing system to generate secure code with large language models (LLMs). SGCode integrates recent prompt-optimization approaches with LLMs in a unified system accessible through front-end and back-end APIs, enabling users to 1) generate secure code, which is free of vulnerabilities, 2) review and share security analysis, and 3) easily switch from one prompt optimization approach to another, while providing insights on model and system performance. We populated SGCode on an AWS server with PromSec, an approach that optimizes prompts by combining an LLM and security tools with a lightweight generative adversarial graph neural network to detect and fix security vulnerabilities in the generated code. Extensive experiments show that SGCode is practical as a public tool to gain insights into the trade-offs between model utility, secure code generation, and system cost. SGCode has only a marginal cost compared with prompting LLMs. SGCode is available at: https://sgcode.codes/.
State-of-the-art neural models of source code tend to be evaluated on the generation of individual expressions and lines of code, and commonly fail on long-horizon tasks such as the generation of entire method bodies. We propose to address this deficiency using weak supervision from a static program analyzer. Our neurosymbolic method allows a deep generative model to symbolically compute, using calls to a static-analysis tool, long-distance semantic relationships in the code that it has already generated. During training, the model observes these relationships and learns to generate programs conditioned on them. We apply our approach to the problem of generating entire Java methods given the remainder of the class that contains the method. Our experiments show that the approach substantially outperforms state-of-the-art transformers and a model that explicitly tries to learn program semantics on this task, both in terms of producing programs free of basic semantic errors and in terms of syntactically matching the ground truth.
Data curation is commonly considered a "secret-sauce" for LLM training, with higher quality data usually leading to better LLM performance. Given the scale of internet-scraped corpora, data pruning has become a larger and larger focus. Specifically, many have shown that de-duplicating data, or sub-selecting higher quality data, can lead to efficiency or performance improvements. Generally, three types of methods are used to filter internet-scale corpora: embedding-based, heuristic-based, and classifier-based. In this work, we contrast the former two in the domain of finetuning LLMs for code generation. We find that embedding-based methods are often confounded by length, and that a simple heuristic--pruning long files--outperforms other methods in compute-limited regimes. Our method can yield up to a 2x efficiency benefit in training (while matching performance) or a 3.5% absolute performance improvement on HumanEval (while matching compute). However, we find that perplexity on held-out long files can increase, begging the question of whether optimizing data mixtures for common coding benchmarks (HumanEval, MBPP) actually best serves downstream use cases. Overall, we hope our work builds useful intuitions about code data (specifically, the low quality of extremely long code files) provides a compelling heuristic-based method for data pruning, and brings to light questions in how we evaluate code generation models.
Ensuring correctness is crucial for code generation. Formal verification offers a definitive assurance of correctness, but demands substantial human effort in proof construction and hence raises a pressing need for automation. The primary obstacle lies in the severe lack of data-there is much fewer proofs than code snippets for Large Language Models (LLMs) to train upon. In this paper, we introduce SAFE, a framework that overcomes the lack of human-written proofs to enable automated proof generation of Rust code. SAFE establishes a self-evolving cycle where data synthesis and fine-tuning collaborate to enhance the model capability, leveraging the definitive power of a symbolic verifier in telling correct proofs from incorrect ones. SAFE also re-purposes the large number of synthesized incorrect proofs to train the self-debugging capability of the fine-tuned models, empowering them to fix incorrect proofs based on the verifier's feedback. SAFE demonstrates superior efficiency and precision compared to GPT-4o. Through tens of thousands of synthesized proofs and the self-debugging mechanism, we improve the capability of open-source models, initially unacquainted with formal verification, to automatically write proofs for Rust code. This advancement leads to a significant improvement in performance, achieving a 52.52% accuracy rate in a benchmark crafted by human experts, a significant leap over GPT-4o's performance of 14.39%.
Zero-shot generalization across various robots, tasks and environments remains a significant challenge in robotic manipulation. Policy code generation methods use executable code to connect high-level task descriptions and low-level action sequences, leveraging the generalization capabilities of large language models and atomic skill libraries. In this work, we propose Robotic Programmer (RoboPro), a robotic foundation model, enabling the capability of perceiving visual information and following free-form instructions to perform robotic manipulation with policy code in a zero-shot manner. To address low efficiency and high cost in collecting runtime code data for robotic tasks, we devise Video2Code to synthesize executable code from extensive videos in-the-wild with off-the-shelf vision-language model and code-domain large language model. Extensive experiments show that RoboPro achieves the state-of-the-art zero-shot performance on robotic manipulation in both simulators and real-world environments. Specifically, the zero-shot success rate of RoboPro on RLBench surpasses the state-of-the-art model GPT-4o by 11.6%, which is even comparable to a strong supervised training baseline. Furthermore, RoboPro is robust to variations on API formats and skill sets.
The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software engineering tasks. However, even with test-time computed reasoning models, these systems still struggle with complex software engineering challenges. This work introduces CURA, a code understanding and reasoning agent system enhanced with verbal process supervision (VPS), achieving a 3.65\% improvement over baseline models on challenging benchmarks like BigCodeBench. Furthermore, CURA, when paired with the o3-mini model and VPS techniques, attains state-of-the-art performance. This work represents a step forward in integrating reasoning-driven architectures with LLM-based code generation, enabling agentic reasoning for language models to solve complex software engineering tasks.
Large Language Models (LLMs) have advanced Verilog code generation significantly, yet face challenges in data quality, reasoning capabilities, and computational efficiency. This paper presents ReasoningV, a novel model employing a hybrid reasoning strategy that integrates trained intrinsic capabilities with dynamic inference adaptation for Verilog code generation. Our framework introduces three complementary innovations: (1) ReasoningV-5K, a high-quality dataset of 5,000 functionally verified instances with reasoning paths created through multi-dimensional filtering of PyraNet samples; (2) a two-stage training approach combining parameter-efficient fine-tuning for foundational knowledge with full-parameter optimization for enhanced reasoning; and (3) an adaptive reasoning mechanism that dynamically adjusts reasoning depth based on problem complexity, reducing token consumption by up to 75\% while preserving performance. Experimental results demonstrate ReasoningV's effectiveness with a pass@1 accuracy of 57.8\% on VerilogEval-human, achieving performance competitive with leading commercial models like Gemini-2.0-flash (59.5\%) and exceeding the previous best open-source model by 10.4 percentage points. ReasoningV offers a more reliable and accessible pathway for advancing AI-driven hardware design automation, with our model, data, and code available at https://github.com/BUAA-CLab/ReasoningV.
The task of code generation from natural language (NL2Code) has become extremely popular, especially with the advent of Large Language Models (LLMs). However, efforts to quantify and track this progress have suffered due to a lack of reliable metrics for functional correctness. While popular benchmarks like HumanEval have test cases to enable reliable evaluation of correctness, it is time-consuming and requires human effort to collect test cases. As an alternative several reference-based evaluation metrics have been proposed, with embedding-based metrics like CodeBERTScore being touted as having a high correlation with human preferences and functional correctness. In our work, we analyze the ability of embedding-based metrics like CodeBERTScore to measure functional correctness and other helpful constructs like editing effort by analyzing outputs of ten models over two popular code generation benchmarks. Our results show that while they have a weak correlation with functional correctness (0.16), they are strongly correlated (0.72) with editing effort.
We improve the performance of the American Fuzzy Lop (AFL) fuzz testing framework by using Generative Adversarial Network (GAN) models to reinitialize the system with novel seed files. We assess performance based on the temporal rate at which we produce novel and unseen code paths. We compare this approach to seed file generation from a random draw of bytes observed in the training seed files. The code path lengths and variations were not sufficiently diverse to fully replace AFL input generation. However, augmenting native AFL with these additional code paths demonstrated improvements over AFL alone. Specifically, experiments showed the GAN was faster and more effective than the LSTM and out-performed a random augmentation strategy, as measured by the number of unique code paths discovered. GAN helps AFL discover 14.23% more code paths than the random strategy in the same amount of CPU time, finds 6.16% more unique code paths, and finds paths that are on average 13.84% longer. Using GAN shows promise as a reinitialization strategy for AFL to help the fuzzer exercise deep paths in software.
Large language models (LLMs) achieve promising results in code generation based on a given natural language description. They have been integrated into open-source projects and commercial products to facilitate daily coding activities. The natural language description in the prompt is crucial for LLMs to comprehend users' requirements. Prior studies uncover that LLMs are sensitive to the changes in the prompts, including slight changes that look inconspicuous. However, the natural language descriptions often vary in real-world scenarios (e.g., different formats, grammar, and wording). Prior studies on the robustness of LLMs are often based on random perturbations and such perturbations may not actually happen. In this paper, we conduct a comprehensive study to investigate how are code LLMs robust to variations of natural language description in real-world scenarios. We summarize 18 categories of perturbations of natural language and 3 combinations of co-occurred categories based on our literature review and an online survey with practitioners. We propose an automated framework, NLPerturbator, which can perform perturbations of each category given a set of prompts. Through a series of experiments on code generation using six code LLMs, we find that the perturbed prompts can decrease the performance of code generation by a considerable margin (e.g., up to 21.2%, and 4.8% to 6.1% on average). Our study highlights the importance of enhancing the robustness of LLMs to real-world variations in the prompts, as well as the essentiality of attentively constructing the prompts.
Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.
Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators. To support this paradigm, we design a dedicated data pipeline and curate two high-quality datasets, Video-Coder-SFT-6k and Video-Coder-RL-2k, which contain diverse prompts and ground-truth reference videos. We further develop the Video- Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference. We then train Video-Coder with SFT fol- lowed by harness-native agentic reinforcement learning with dual reward feedback, which combines execution-based and video-based rewards. Additionally, we design an annealing training strategy that gradually reduces the execution reward over time, allowing the model to rely more on the video reward in the later training stages. Experiments show that Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0. We hope this work can serve as an open foundation for coding agents in video generation, and we fully open-source our data, models, and code
Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decomposition capabilities. To address this issue, we propose a reasoning-augmented data generation process, SRA-MCTS, which guides the model to autonomously generate high-quality intermediate reasoning paths. This creates a positive feedback loop, enabling continuous improvement. Our method operates entirely through the model itself without requiring additional supervision. By synthesizing natural language reasoning paths and translating them into executable code, the approach ensures analytical accuracy and enhances the success rate in solving complex tasks. Experimental results show that, even without additional supervisory signals, our method achieves performance improvements across different model scales, demonstrating the significant potential of self-improvement in small models. Furthermore, the method remains robust when traditional Chain-of-Thought (CoT) approaches exhibit performance degradation, with notable improvements observed in diversity metrics such as pass@10. We encourage further exploration of reasoning processes within training data to enhance the ability of language models to address complex problems. Our code and data are public at https://github.com/DIRECT-BIT/SRA-MCTS.
Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive context, there is a need to systematically assess this new setup: LLMs entail a well-documented set of risks for safety-related systems' development due to their stochastic nature. To reduce the effort for code reviewers to evaluate LLM-generated code, we propose an evaluation pipeline to conduct sanity-checks on the generated code. We compare the performance of six state-of-the-art LLMs (CodeLlama, CodeGemma, DeepSeek-r1, DeepSeek-Coders, Mistral, and GPT-4) on four safety-related programming tasks. Additionally, we qualitatively analyse the most frequent faults generated by these LLMs, creating a failure-mode catalogue to support human reviewers. Finally, the limitations and capabilities of LLMs in code generation, and the use of the proposed pipeline in the existing process, are discussed.
Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like HumanEval and MBPP. Thus, a natural question is, would LLMs have similar performance in real world coding tasks as their performance in these benchmarks? Unfortunately, one cannot answer this question, since these benchmarks consist of short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks. To address these challenges, we create REPOCOD, a Python code-generation benchmark containing complex tasks with realistic dependencies in real-world large projects and appropriate metrics for evaluating source code. It includes 980 whole-function generation tasks from 11 popular projects, 50.8% of which require repository-level context. REPOCOD includes 314 developer-written test cases per instance for better evaluation. We evaluate ten LLMs on REPOCOD and find that none achieves more than 30% pass@1 on REPOCOD, indicating the necessity of building stronger LLMs that can help developers in real-world software development. In addition, we found that retrieval-augmented generation achieves better results than using target function dependencies as context.
Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands both expert knowledge and iterative refinement. Leveraging recent advancements in large language models (LLMs) and their structured text generation capabilities, we propose VeriMind, an agentic LLM framework for Verilog code generation that significantly automates and optimizes the synthesis process. Unlike traditional LLM-based code generators, VeriMind employs a structured reasoning approach: given a user-provided prompt describing design requirements, the system first formulates a detailed train of thought before the final Verilog code is generated. This multi-step methodology enhances interpretability, accuracy, and adaptability in hardware design. In addition, we introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement. Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3\%$ improvement on pass@k metric and $8.1\%$ on pass@ARC metric. These findings underscore the transformative potential of agentic LLMs in automated hardware design, RTL development, and digital system synthesis.
Large Language Models (LLMs) are advanced Artificial Intelligence (AI) systems that have undergone extensive training using large datasets in order to understand and produce language that closely resembles that of humans. These models have reached a level of proficiency where they are capable of successfully completing university exams across several disciplines and generating functional code to handle novel problems. This research investigates the coding proficiency of ChatGPT 3.5, a LLM released by OpenAI in November 2022, which has gained significant recognition for its impressive text generating and code creation capabilities. The skill of the model in creating code snippets is evaluated across 10 various programming languages and 4 different software domains. Based on the findings derived from this research, major unexpected behaviors and limitations of the model have been identified. This study aims to identify potential areas for development and examine the ramifications of automated code generation on the evolution of programming languages and on the tech industry.