Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence shown by the large language models, their specificity in code generation can still be improved due to the syntactic gap and mismatched vocabulary existing between natural language and programming languages. In this paper, we propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework that bridges the gap between NL and PL to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge, which can facilitate natural language based LLMs for better understanding of code syntax and serve as a bridge among different programming languages. To take the extracted structural knowledge into the foundation models, we propose 1) a hard meta-graph prompt template to transform the challenging syntax graph into informative graphical view for tuning-free models and 2) a soft prompting technique that injects the domain knowledge of programming languages into model parameters via finetuning the models with the soft signals encoded by GNN expert model. Specifically, two constraints are designed to improve the alignment and structure expressiveness, contributing to the informativeness of the single-token-sized external <GraphEmb> for enhanced code generation. CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation. Implementation is available at https://anonymous.4open.science/r/Code-5970/ .
Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and accessibility. While benchmarks (e.g. HumanEval/LiveCodeBench) evaluate code generation and real-world relevance, previous works ignore the scenario of modifying code in repositories. Considering challenges remaining in improving reflection capabilities and avoiding data contamination in dynamic benchmarks, we introduce LiveRepoReflection, a challenging benchmark for evaluating code understanding and generation in multi-file repository contexts, featuring 1,888 rigorously filtered test cases across $6$ programming languages to ensure diversity, correctness, and high difficulty. Further, we create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources, used to train RepoReflectionCoder through a two-turn dialogue process involving code generation and error-driven repair. The leaderboard evaluates over 40 LLMs to reflect the model performance of repository-based code reflection.
As hardware design complexity escalates, there is an urgent need for advanced automation in electronic design automation (EDA). Traditional register transfer level (RTL) design methods are manual, time-consuming, and prone to errors. While commercial (instruction-tuned) large language models (LLMs) shows promising performance for automation, they pose security and privacy concerns. Open-source models offer alternatives; however, they frequently fall short in quality/correctness, largely due to limited, high-quality RTL code data essential for effective training and generalization. This paper proposes RTL++, a first-of-its-kind LLM-assisted method for RTL code generation that utilizes graph representations of code structures to enhance the quality of generated code. By encoding RTL code into a textualized control flowgraphs (CFG) and data flow graphs (DFG), RTL++ captures the inherent hierarchy, dependencies, and relationships within the code. This structured graph-based approach enhances the context available to LLMs, enabling them to better understand and generate instructions. By focusing on data generation through graph representations, RTL++ addresses the limitations of previous approaches that rely solely on code and suffer from lack of diversity. Experimental results demonstrate that RTL++ outperforms state-of-the-art models fine-tuned for RTL generation, as evaluated using the VerilogEval benchmark's Pass@1/5/10 metric, as well as the RTLLM1.1 model, which highlight the effectiveness of graph-enhanced context in advancing the capabilities of LLM-assisted RTL code generation.
We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis, where the LLM outputs executable programs that map environment states to action sequences. Our proposed architecture incorporates several prompting strategies, including direct code generation, pseudocode-conditioned refinement, and curriculum-based prompting, but also includes an iterative refinement mechanism that updates code based on task performance feedback. We evaluate our approach using six leading LLMs and two challenging grid-based benchmarks (GRASP and MiniGrid). Our IPP framework demonstrates improvements over direct code generation ranging from 10\% to as much as 10x across five of the six models and establishes a new state-of-the-art result for GRASP. IPP is found to significantly outperform direct elicitation of a solution from GPT-o3-mini (by 63\% on MiniGrid to 116\% on GRASP), demonstrating the viability of the overall approach. Computational costs of all code generation approaches are similar. While code generation has a higher initial prompting cost compared to direct solution elicitation (\$0.08 per task vs. \$0.002 per instance for GPT-o3-mini), the code can be reused for any number of instances, making the amortized cost significantly lower (by 400x on GPT-o3-mini across the complete GRASP benchmark).
Rapid progress in high-level task planning and code generation for open-world robot manipulation has been witnessed in Embodied AI. However, previous studies put much effort into general common sense reasoning and task planning capabilities of large-scale language or multi-modal models, relatively little effort on ensuring the deployability of generated code on real robots, and other fundamental components of autonomous robot systems including robot perception, motion planning, and control. To bridge this ``ideal-to-real'' gap, this paper presents \textbf{RobotScript}, a platform for 1) a deployable robot manipulation pipeline powered by code generation; and 2) a code generation benchmark for robot manipulation tasks in free-form natural language. The RobotScript platform addresses this gap by emphasizing the unified interface with both simulation and real robots, based on abstraction from the Robot Operating System (ROS), ensuring syntax compliance and simulation validation with Gazebo. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms, and multiple grippers. Additionally, our benchmark assesses reasoning abilities for physical space and constraints, highlighting the differences between GPT-3.5, GPT-4, and Gemini in handling complex physical interactions. Finally, we present a thorough evaluation on the whole system, exploring how each module in the pipeline: code generation, perception, motion planning, and even object geometric properties, impact the overall performance of the system.
Large Language Models (LLMs) have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in generating correct code, in an iterative process. While effective, these methods could be costly and time-consuming due to numerous interactions with the LLM and the extensive token usage. To address this issue, we propose an alternative approach named Evolutionary Prompt Engineering for Code (EPiC), which leverages a lightweight evolutionary algorithm to evolve the original prompts toward better ones that produce high-quality code, with minimal interactions with LLM. Our evaluation against state-of-the-art (SOTA) LLM-based code generation models shows that EPiC outperforms all the baselines in terms of cost-effectiveness.
Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL). Due to this oversight, a better decoding strategy for code generation remains an open question. In this paper, we conduct the first systematic study to explore a decoding strategy specialized in code generation. With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred. Among them, the challenging tokens mainly appear at the beginning of a code block. Inspired by the above findings, we propose a simple yet effective method: Adaptive Temperature (AdapT) sampling, which dynamically adjusts the temperature coefficient when decoding different tokens. We apply a larger temperature when sampling for challenging tokens, allowing LLMs to explore diverse choices. We employ a smaller temperature for confident tokens avoiding the influence of tail randomness noises. We apply AdapT sampling to LLMs with different sizes and conduct evaluations on two popular datasets. Results show that AdapT sampling significantly outperforms state-of-the-art decoding strategy.
In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code comprehension and generation tasks and sometimes even better than small SOTA models specifically fine-tuned on each downstream task. We also find that larger instructed LLMs are not always better on code-related tasks. Second, for the few-shot setting, we find that adding demonstration examples substantially helps instructed LLMs perform better on most code comprehension and generation tasks; however, the examples would sometimes induce unstable or even worse performance. Furthermore, we find widely-used BM25-based shot selection strategy significantly outperforms the basic random selection or fixed selection only on generation problems. Third, for the fine-tuning setting, we find that fine-tuning could further improve the model performance on downstream code comprehension and generation tasks compared to the zero-shot/one-shot performance. In addition, after being fine-tuned on the same downstream task dataset, instructed LLMs outperform both the small SOTA models and similar-scaled LLMs without instruction tuning. Based on our findings, we further present practical implications on model and usage recommendation, performance and cost trade-offs, and future direction.
Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they do not easily allow reconsidering earlier tokens generated. We introduce CodeFusion, a pre-trained diffusion code generation model that addresses this limitation by iteratively denoising a complete program conditioned on the encoded natural language. We evaluate CodeFusion on the task of natural language to code generation for Bash, Python, and Microsoft Excel conditional formatting (CF) rules. Experiments show that CodeFusion (75M parameters) performs on par with state-of-the-art auto-regressive systems (350M-175B parameters) in top-1 accuracy and outperforms them in top-3 and top-5 accuracy due to its better balance in diversity versus quality.
Large language models (LLMs) have shown strong performance in Verilog generation from natural language description. However, ensuring the functional correctness of the generated code remains a significant challenge. This paper introduces a method that integrates verification insights from testbench into the training of Verilog generation LLMs, aligning the training with the fundamental goal of hardware design: functional correctness. The main obstacle in using LLMs for Verilog code generation is the lack of sufficient functional verification data, particularly testbenches paired with design specifications and code. To address this problem, we introduce an automatic testbench generation pipeline that decomposes the process and uses feedback from the Verilog compiler simulator (VCS) to reduce hallucination and ensure correctness. We then use the testbench to evaluate the generated codes and collect them for further training, where verification insights are introduced. Our method applies reinforcement learning (RL), specifically direct preference optimization (DPO), to align Verilog code generation with functional correctness by training preference pairs based on testbench outcomes. In evaluations on VerilogEval-Machine, VerilogEval-Human, RTLLM v1.1, RTLLM v2, and VerilogEval v2, our approach consistently outperforms state-of-the-art baselines in generating functionally correct Verilog code. We open source all training code, data, and models at https://anonymous.4open.science/r/VeriPrefer-E88B.
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments. To tackle this issue, we propose ReCode (rule-based Reinforcement learning for Code Update), a novel framework that mimics human programmer adaptation to API changes. Specifically, we construct a dataset of approximately 2,000 data entries to train the LLMs to perform version migration based on updated information. Then, we introduce a modified string similarity metric for code evaluation as the reward for reinforcement learning. Our experiments demonstrate that ReCode substantially boosts LLMs' code generation performance in dynamic API scenarios, especially on the unseen CodeUpdateArena task. Crucially, compared to supervised fine-tuning, ReCode has less impact on LLMs' general code generation abilities. We apply ReCode on various LLMs and reinforcement learning algorithms (GRPO and DAPO), all achieving consistent improvements. Notably, after training, Qwen2.5-Coder-7B outperforms that of the 32B parameter code instruction-tuned model and the reasoning model with the same architecture. Code is available at https://github.com/zjunlp/ReCode.
While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation. We first let LLMs classify the type of the circuit based on the specifications. Then, according to the type of the circuit, we split the tasks into several sub-procedures, including information extraction and human-like design flow using Electronic Design Automation (EDA) tools. Besides, we also use a search method to mitigate the variation in code generation. Experimental results show that our method can significantly improve the functional correctness of the generated Verilog and reduce the hallucination of LLMs.
Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, PA3. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.
Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPl-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Notably, ReflectionCoder-DeepSeek-Coder-33B reaches pass@1 of 82.9 (76.8) on HumanEval (+) and 84.1 (72.0) on MBPP (+), on par with GPT-3.5-Turbo and Claude-3-opus, and surpasses early GPT-4. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.
Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existing code generation benchmarks primarily assess the functional correctness of code generated by LLMs in single-turn interactions, offering limited insight into their capabilities to generate code that strictly follows users' instructions, especially in multi-turn interaction scenarios. In this paper, we introduce CodeIF-Bench, a benchmark for evaluating LLMs' instruction-following capabilities in interactive code generation. Specifically, CodeIF-Bench incorporates nine types of verifiable instructions aligned with the real-world software development requirements, which can be independently and objectively validated through specified test cases, facilitating the evaluation of instruction-following capability in multi-turn interactions. We evaluate nine prominent LLMs using CodeIF-Bench, and the experimental results reveal a significant disparity between their basic programming capability and instruction-following capability, particularly as task complexity, context length, and the number of dialogue rounds increase.
Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest. Progress in these areas has been limited by the low availability of parallel corpora of code and natural language descriptions, which tend to be small and constrained to specific domains. In this work we introduce a large and diverse parallel corpus of a hundred thousands Python functions with their documentation strings ("docstrings") generated by scraping open source repositories on GitHub. We describe baseline results for the code documentation and code generation tasks obtained by neural machine translation. We also experiment with data augmentation techniques to further increase the amount of training data. We release our datasets and processing scripts in order to stimulate research in these areas.
Recently, there has been increasing activity in using deep learning for software engineering, including tasks like code generation and summarization. In particular, the most recent coding Large Language Models seem to perform well on these problems. In this technical report, we aim to review how these models perform in code explanation/summarization, while also investigating their code generation capabilities (based on natural language descriptions).
This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretrained (PT) and instruction-tuned (IT) variants have remarkably resilient natural language understanding, excel in mathematical reasoning, and match code capabilities of other open models. CodeGemma 2B is a state-of-the-art code completion model designed for fast code infilling and open-ended generation in latency-sensitive settings.
Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CodeSwift, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CodeSwift constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CodeSwift reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CodeSwift can reach up to 2.53x and 2.54x speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%.
Code generation aims to understand the problem description and generate corresponding code snippets, where existing works generally decompose such complex tasks into intermediate steps by prompting strategies, such as Chain-of-Thought and its variants. While these studies have achieved some success, their effectiveness is highly dependent on the capabilities of advanced Large Language Models (LLMs) such as GPT-4, particularly in terms of API calls, which significantly limits their practical applicability. Consequently, how to enhance the code generation capabilities of small and medium-scale code LLMs without significantly increasing training costs is an appealing challenge. In this paper, we suggest that code comments are the natural logic pivot between natural language and code language and propose using comments to boost the code generation ability of code LLMs. Concretely, we propose MANGO (comMents As Natural loGic pivOts), including a comment contrastive training strategy and a corresponding logical comment decoding strategy. Experiments are performed on HumanEval and MBPP, utilizing StarCoder and WizardCoder as backbone models, and encompassing model parameter sizes between 3B and 7B. The results indicate that MANGO significantly improves the code pass rate based on the strong baselines. Meanwhile, the robustness of the logical comment decoding strategy is notably higher than the Chain-of-thoughts prompting. The code is publicly available at \url{https://github.com/pppa2019/Mango}.