In arbitrary-order language models, it is an open question how to sample tokens in parallel from the correct joint distribution. With discrete diffusion models, the more tokens they generate in parallel, the less their predicted distributions adhere to the originally learned data distribution, as they rely on a conditional independence assumption that only works with infinitesimally small timesteps. We find that a different class of models, any-subset autoregressive models (AS-ARMs), holds the solution. As implied by the name, AS-ARMs can generate tokens in any order, and in parallel. Moreover, AS-ARMs support parallelized joint probability density estimation, allowing them to correct their own parallel-generated token distributions, via our Any-Subset Speculative Decoding (ASSD) algorithm. ASSD provably enables generation of tokens from the correct joint distribution, with the number of neural network calls upper bounded by the number of tokens predicted. We empirically verify that ASSD speeds up language generation, without sacrificing quality. Furthermore, we provide a mathematically justified scheme for training AS-ARMs for generation, and show that AS-ARMs achieve state-of-the-art performance among sub-200M parameter models on infilling benchmark tasks, and nearly match the performance of models 50X larger on code generation. Our theoretical and empirical results indicate that the once-forgotten AS-ARMs are a promising direction of language modeling.
In supercomputing, efficient and optimized code generation is essential to leverage high-performance systems effectively. We propose Agentic Retrieval-Augmented Code Synthesis (ARCS), an advanced framework for accurate, robust, and efficient code generation, completion, and translation. ARCS integrates Retrieval-Augmented Generation (RAG) with Chain-of-Thought (CoT) reasoning to systematically break down and iteratively refine complex programming tasks. An agent-based RAG mechanism retrieves relevant code snippets, while real-time execution feedback drives the synthesis of candidate solutions. This process is formalized as a state-action search tree optimization, balancing code correctness with editing efficiency. Evaluations on the Geeks4Geeks and HumanEval benchmarks demonstrate that ARCS significantly outperforms traditional prompting methods in translation and generation quality. By enabling scalable and precise code synthesis, ARCS offers transformative potential for automating and optimizing code development in supercomputing applications, enhancing computational resource utilization.
Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specific APIs, posing barriers for many users. While Large Language Models (LLMs) can generate code from natural language queries, runtime code generation is severely limited due to unverified code, security risks, longer response times, and higher computational costs. To bridge the gap, we propose an offline simulation framework to curate a software-specific skillset, a collection of verified scripts, by exploiting LLMs and publicly available scripting guides. Our framework comprises two components: (1) task creation, using top-down functionality guidance and bottom-up API synergy exploration to generate helpful tasks; and (2) skill generation with trials, refining and validating scripts based on execution feedback. To efficiently navigate the extensive API landscape, we introduce a Graph Neural Network (GNN)-based link prediction model to capture API synergy, enabling the generation of skills involving underutilized APIs and expanding the skillset's diversity. Experiments with Adobe Illustrator demonstrate that our framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation. This is the first attempt to use software scripting interfaces as a testbed for LLM-based systems, highlighting the advantages of leveraging execution feedback in a controlled environment and offering valuable insights into aligning AI capabilities with user needs in specialized software domains.
Machine Learning (ML) research is spread through academic papers featuring rich multimodal content, including text, diagrams, and tabular results. However, translating these multimodal elements into executable code remains a challenging and time-consuming process that requires substantial ML expertise. We introduce ``Paper-to-Code'' (P2C), a novel task that transforms the multimodal content of scientific publications into fully executable code repositories, which extends beyond the existing formulation of code generation that merely converts textual descriptions into isolated code snippets. To automate the P2C process, we propose AutoP2C, a multi-agent framework based on large language models that processes both textual and visual content from research papers to generate complete code repositories. Specifically, AutoP2C contains four stages: (1) repository blueprint extraction from established codebases, (2) multimodal content parsing that integrates information from text, equations, and figures, (3) hierarchical task decomposition for structured code generation, and (4) iterative feedback-driven debugging to ensure functionality and performance. Evaluation on a benchmark of eight research papers demonstrates the effectiveness of AutoP2C, which can successfully generate executable code repositories for all eight papers, while OpenAI-o1 or DeepSeek-R1 can only produce runnable code for one paper. The code is available at https://github.com/shoushouyu/Automated-Paper-to-Code.
With the rapid development and widespread application of Large Language Models (LLMs), multidimensional evaluation has become increasingly critical. However, current evaluations are often domain-specific and overly complex, limiting their effectiveness as cross-domain proxies for core capabilities. To address these limitations and enable a unified and simple evaluation framework, an ideal proxy task should target a basic capability that generalizes across tasks and is independent of domain-specific knowledge. Turing machine provides a powerful theoretical lens by reducing complex processes to basic, domain-agnostic computational operations. This perspective offers a principled framework for evaluating basic computational abilities essential to a wide range of tasks. Motivated by this abstraction, we introduce \textbf{Turing Machine Bench}, a benchmark designed to assess the ability of LLMs to \textbf{strictly follow rules} and \textbf{accurately manage internal states} for multi-step, referred to as \textbf{computational reasoning}. TMBench incorporates four key features: self-contained and knowledge-agnostic reasoning, a minimalistic multi-step structure, controllable difficulty, and a solid theoretical foundation based on Turing machine. Empirical results demonstrate that TMBench serves as an effective proxy for evaluating computational reasoning on representative LLMs. It produces clear step-wise accuracy curves, revealing LLMs' ability to execute multi-step reasoning processes. By analyzing performance trends across TMBench and established reasoning benchmarks, we find strong correlations with real-world tasks, bridging real-task evaluation with basic ability assessment. These findings suggest that TMBench holds potential as a cross-domain dimension for evaluating reasoning in LLMs. Code and data are available at \href{https://github.com/HaitaoWuTJU/Turing-Machine-Bench}{Repo}.
Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing codes. We formalize this iterative, multi-turn paradigm as codeflow and introduce CodeFlowBench, the first benchmark designed to comprehensively evaluate LLMs' ability to perform codeflow, namely implementing new functionality by reusing existing functions over multiple turns. CodeFlowBench comprises 5,258 problems from Codeforces and is continuously updated via an automated pipeline, which decomposes each problem into subproblems with unit tests based on dependency tree analysis and dataflow analysis. We further propose a novel evaluation framework featured dual assessment protocol and structural metrics derived from dependency trees. Extensive experiments on 16 popular LLMs reveal significant performance degradation in multi-turn scenarios. For instance, o1-mini retains only 20.8% Pass@1 in multi-turn scenario versus 37.8% in single-turn scenario. More fine-grained analysis illustrates that model performance inversely correlates with dependency complexity. These findings not only highlight the critical challenges for supporting real-world workflows, but also establish CodeFlowBench as an essential tool for advancing code generation research.
We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) in generating complete specification code pertaining to operating system kernel verification tasks. The benchmark first defines the specification generation problem into a program synthesis problem within a confined scope of syntax and semantics by providing LLMs with the programming model. The LLMs are required to understand the provided verification assumption and the potential syntax and semantics space to search for, then generate the complete specification for the potentially buggy operating system code implementation under the guidance of the high-level functional description of the operating system. This benchmark is built upon a real-world operating system kernel, Hyperkernel, and consists of 245 complex specification generation tasks in total, each is a long context task of about 20k-30k tokens. Our comprehensive evaluation of 12 LLMs exhibits the limited performance of the current LLMs on the specification generation tasks for operating system verification. Significant disparities in their performance on the benchmark highlight differences in their ability to handle long-context code generation tasks. The evaluation toolkit and benchmark are available at https://github.com/lishangyu-hkust/OSVBench.
Heterogeneous deep learning systems (DLS) such as GPUs and ASICs have been widely deployed in industrial data centers, which requires to develop multiple low-level tensor programs for different platforms. An attractive solution to relieve the programming burden is to transcompile the legacy code of one platform to others. However, current transcompilation techniques struggle with either tremendous manual efforts or functional incorrectness, rendering "Write Once, Run Anywhere" of tensor programs an open question. We propose a novel transcompiler, i.e., QiMeng-Xpiler, for automatically translating tensor programs across DLS via both large language models (LLMs) and symbolic program synthesis, i.e., neural-symbolic synthesis. The key insight is leveraging the powerful code generation ability of LLM to make costly search-based symbolic synthesis computationally tractable. Concretely, we propose multiple LLM-assisted compilation passes via pre-defined meta-prompts for program transformation. During each program transformation, efficient symbolic program synthesis is employed to repair incorrect code snippets with a limited scale. To attain high performance, we propose a hierarchical auto-tuning approach to systematically explore both the parameters and sequences of transformation passes. Experiments on 4 DLS with distinct programming interfaces, i.e., Intel DL Boost with VNNI, NVIDIA GPU with CUDA, AMD MI with HIP, and Cambricon MLU with BANG, demonstrate that QiMeng-Xpiler correctly translates different tensor programs at the accuracy of 95% on average, and the performance of translated programs achieves up to 2.0x over vendor-provided manually-optimized libraries. As a result, the programming productivity of DLS is improved by up to 96.0x via transcompiling legacy tensor programs.
The demand for high-fidelity test data is paramount in industrial settings where access to production data is largely restricted. Traditional data generation methods often fall short, struggling with low-fidelity and the ability to model complex data structures and semantic relationships that are critical for testing complex SQL code generation services like Natural Language to SQL (NL2SQL). In this paper, we address the critical need for generating syntactically correct and semantically ``meaningful'' mock data for complex schema that includes columns with nested structures that we frequently encounter in Google SQL code generation workloads. We highlight the limitations of existing approaches used in production, particularly their inability to handle large and complex schema, as well as the lack of semantically coherent test data that lead to limited test coverage. We demonstrate that by leveraging Large Language Models (LLMs) and incorporating strategic pre- and post-processing steps, we can generate realistic high-fidelity test data that adheres to complex structural constraints and maintains semantic integrity to the test targets (SQL queries/functions). This approach supports comprehensive testing of complex SQL queries involving joins, aggregations, and even deeply nested subqueries, ensuring robust evaluation of SQL code generation services, like NL2SQL and SQL Code Assistant services. Our results demonstrate the practical utility of an out-of-the-box LLM (\textit{gemini}) based test data generation for industrial SQL code generation services where generating realistic test data is essential due to the frequent unavailability of production datasets.
Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full hardware utilization. We present PipeSpec, a framework that generalizes speculative decoding to $k$ models arranged in a hierarchical pipeline, enabling asynchronous execution with lightweight coordination for prediction verification and rollback. Our analytical model characterizes token generation rates across pipeline stages and proves guaranteed throughput improvements over traditional decoding for any non-zero acceptance rate. We further derive closed-form expressions for steady-state verification probabilities that explain the empirical benefits of pipeline depth. Experimental results show that PipeSpec achieves up to 2.54$\times$ speedup while outperforming state-of-the-art methods. We validate PipeSpec across text summarization and code generation tasks using LLaMA 2 and 3 models, demonstrating that pipeline efficiency increases with model depth, providing a scalable approach to accelerating LLM inference on multi-device systems.
Linear Programming (LP) problems aim to find the optimal solution to an objective under constraints. These problems typically require domain knowledge, mathematical skills, and programming ability, presenting significant challenges for non-experts. This study explores the efficiency of Large Language Models (LLMs) in generating solver-specific LP code. We propose CHORUS, a retrieval-augmented generation (RAG) framework for synthesizing Gurobi-based LP code from natural language problem statements. CHORUS incorporates a hierarchical tree-like chunking strategy for theoretical contents and generates additional metadata based on code examples from documentation to facilitate self-contained, semantically coherent retrieval. Two-stage retrieval approach of CHORUS followed by cross-encoder reranking further ensures contextual relevance. Finally, expertly crafted prompt and structured parser with reasoning steps improve code generation performance significantly. Experiments on the NL4Opt-Code benchmark show that CHORUS improves the performance of open-source LLMs such as Llama3.1 (8B), Llama3.3 (70B), Phi4 (14B), Deepseek-r1 (32B), and Qwen2.5-coder (32B) by a significant margin compared to baseline and conventional RAG. It also allows these open-source LLMs to outperform or match the performance of much stronger baselines-GPT3.5 and GPT4 while requiring far fewer computational resources. Ablation studies further demonstrate the importance of expert prompting, hierarchical chunking, and structured reasoning.
The performance of large language models (LLMs) in program synthesis and mathematical reasoning is fundamentally limited by the quality of their pre-training corpora. We introduce two openly licensed datasets, released under the Llama 3.3 Community License, that significantly enhance LLM performance by systematically rewriting public data. SwallowCode (approximately 16.1 billion tokens) refines Python snippets from The-Stack-v2 through a novel four-stage pipeline: syntax validation, pylint-based style filtering, and a two-stage LLM rewriting process that enforces style conformity and transforms snippets into self-contained, algorithmically efficient examples. Unlike prior methods that rely on exclusionary filtering or limited transformations, our transform-and-retain approach upgrades low-quality code, maximizing data utility. SwallowMath (approximately 2.3 billion tokens) enhances Finemath-4+ by removing boilerplate, restoring context, and reformatting solutions into concise, step-by-step explanations. Within a fixed 50 billion token training budget, continual pre-training of Llama-3.1-8B with SwallowCode boosts pass@1 by +17.0 on HumanEval and +17.7 on HumanEval+ compared to Stack-Edu, surpassing the baseline model's code generation capabilities. Similarly, substituting SwallowMath yields +12.4 accuracy on GSM8K and +7.6 on MATH. Ablation studies confirm that each pipeline stage contributes incrementally, with rewriting delivering the largest gains. All datasets, prompts, and checkpoints are publicly available, enabling reproducible research and advancing LLM pre-training for specialized domains.
Large language models (LLMs) excel at generating code from natural language instructions, yet they often lack an understanding of security vulnerabilities. This limitation makes it difficult for LLMs to avoid security risks in generated code, particularly in high-security programming tasks such as smart contract development for blockchain. Researchers have attempted to enhance the vulnerability awareness of these models by training them to differentiate between vulnerable and fixed code snippets. However, this approach relies heavily on manually labeled vulnerability data, which is only available for popular languages like Python and C++. For low-resource languages like Solidity, used in smart contracts, large-scale annotated datasets are scarce and difficult to obtain. To address this challenge, we introduce CodeBC, a code generation model specifically designed for generating secure smart contracts in blockchain. CodeBC employs a three-stage fine-tuning approach based on CodeLlama, distinguishing itself from previous methods by not relying on pairwise vulnerability location annotations. Instead, it leverages vulnerability and security tags to teach the model the differences between vulnerable and secure code. During the inference phase, the model leverages security tags to generate secure and robust code. Experimental results demonstrate that CodeBC outperforms baseline models in terms of BLEU, CodeBLEU, and compilation pass rates, while significantly reducing vulnerability rates. These findings validate the effectiveness and cost-efficiency of our three-stage fine-tuning strategy, making CodeBC a promising solution for generating secure smart contract code.
The rapid advancement of Large Language Models (LLMs) has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code generated by LLMs has been shown to generate insecure code in controlled environments, raising critical concerns about their reliability and security in real-world applications. This paper uses predefined security parameters to evaluate the security compliance of LLM-generated code across multiple models, such as ChatGPT, DeepSeek, Claude, Gemini and Grok. The analysis reveals critical vulnerabilities in authentication mechanisms, session management, input validation and HTTP security headers. Although some models implement security measures to a limited extent, none fully align with industry best practices, highlighting the associated risks in automated software development. Our findings underscore that human expertise is crucial to ensure secure software deployment or review of LLM-generated code. Also, there is a need for robust security assessment frameworks to enhance the reliability of LLM-generated code in real-world applications.
Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach.
Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by the public, face significant security challenges; in particular, configuration files originally intended to set up models by specifying parameters and initial settings can be exploited to execute unauthorized code, yet research has largely overlooked their security compared to that of the models themselves; in this work, we present the first comprehensive study of malicious configurations on Hugging Face, identifying three attack scenarios (file, website, and repository operations) that expose inherent risks; to address these threats, we introduce CONFIGSCAN, an LLM-based tool that analyzes configuration files in the context of their associated runtime code and critical libraries, effectively detecting suspicious elements with low false positive rates and high accuracy; our extensive evaluation uncovers thousands of suspicious repositories and configuration files, underscoring the urgent need for enhanced security validation in AI model hosting platforms.
We introduce STORY2GAME, a novel approach to using Large Language Models to generate text-based interactive fiction games that starts by generating a story, populates the world, and builds the code for actions in a game engine that enables the story to play out interactively. Whereas a given set of hard-coded actions can artificially constrain story generation, the ability to generate actions means the story generation process can be more open-ended but still allow for experiences that are grounded in a game state. The key to successful action generation is to use LLM-generated preconditions and effects of actions in the stories as guides for what aspects of the game state must be tracked and changed by the game engine when a player performs an action. We also introduce a technique for dynamically generating new actions to accommodate the player's desire to perform actions that they think of that are not part of the story. Dynamic action generation may require on-the-fly updates to the game engine's state representation and revision of previously generated actions. We evaluate the success rate of action code generation with respect to whether a player can interactively play through the entire generated story.
The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research. Github repository: https://github.com/observerw/ChiseLLM
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.
Recent advances in Large Language Models (LLMs) have sparked growing interest in applying them to Electronic Design Automation (EDA) tasks, particularly Register Transfer Level (RTL) code generation. While several RTL datasets have been introduced, most focus on syntactic validity rather than functional validation with tests, leading to training examples that compile but may not implement the intended behavior. We present VERICODER, a model for RTL code generation fine-tuned on a dataset validated for functional correctness. This fine-tuning dataset is constructed using a novel methodology that combines unit test generation with feedback-directed refinement. Given a natural language specification and an initial RTL design, we prompt a teacher model (GPT-4o-mini) to generate unit tests and iteratively revise the RTL design based on its simulation results using the generated tests. If necessary, the teacher model also updates the tests to ensure they comply with the natural language specification. As a result of this process, every example in our dataset is functionally validated, consisting of a natural language description, an RTL implementation, and passing tests. Fine-tuned on this dataset of over 125,000 examples, VERICODER achieves state-of-the-art metrics in functional correctness on VerilogEval and RTLLM, with relative gains of up to 71.7% and 27.4% respectively. An ablation study further shows that models trained on our functionally validated dataset outperform those trained on functionally non-validated datasets, underscoring the importance of high-quality datasets in RTL code generation.