Recent LLMs have demonstrated sophisticated problem-solving capabilities on various benchmarks through advanced reasoning algorithms. However, the key research question of identifying reasoning steps that balance complexity and computational efficiency remains unsolved. Recent research has increasingly drawn upon psychological theories to explore strategies for optimizing cognitive pathways. The LLM's final outputs and intermediate steps are regarded as System 1 and System 2, respectively. However, an in-depth exploration of the System 2 reasoning is still lacking. Therefore, we propose a novel psychologically backed Scaffold Reasoning framework for code debugging, which encompasses the Scaffold Stream, Analytic Stream, and Integration Stream. The construction of reference code within the Scaffold Stream is integrated with the buggy code analysis results produced by the Analytic Stream through the Integration Stream. Our framework achieves an 88.91% pass rate and an average inference time of 5.36 seconds per-problem on DebugBench, outperforming other reasoning approaches across various LLMs in both reasoning accuracy and efficiency. Further analyses elucidate the advantages and limitations of various cognitive pathways across varying problem difficulties and bug types. Our findings also corroborate the alignment of the proposed Scaffold Reasoning framework with human cognitive processes.

AI-based code generation is increasingly prevalent, with GitHub Copilot estimated to generate 46% of the code on GitHub. Accurately evaluating how well generated code aligns with developer intent remains a critical challenge. Traditional evaluation methods, such as unit tests, are often unscalable and costly. Syntactic similarity metrics (e.g., BLEU, ROUGE) fail to capture code functionality, and metrics like CodeBERTScore require reference code, which is not always available. To address the gap in reference-free evaluation, with few alternatives such as ICE-Score, this paper introduces MATCH, a novel reference-free metric. MATCH uses Contrastive Learning to generate meaningful embeddings for code and natural language task descriptions, enabling similarity scoring that reflects how well generated code implements the task. We show that MATCH achieves stronger correlations with functional correctness and human preference than existing metrics across multiple programming languages.

Recent frontier-level LLMs have saturated many previously difficult benchmarks, leaving little room for further differentiation. This progress highlights the need for challenging benchmarks that provide objective verification. In this paper, we introduce MCBench, a benchmark designed to evaluate whether LLMs can execute string-matching NLP metrics by strictly following step-by-step instructions. Unlike prior benchmarks that depend on subjective judgments or general reasoning, MCBench offers an objective, deterministic and codeverifiable evaluation. This setup allows us to systematically test whether LLMs can maintain accurate step-by-step execution, including instruction adherence, numerical computation, and long-range consistency in handling intermediate results. To ensure objective evaluation of these abilities, we provide a parallel reference code that can evaluate the accuracy of LLM output. We provide three evaluative metrics and three benchmark variants designed to measure the detailed instruction understanding capability of LLMs. Our analyses show that MCBench serves as an effective and objective tool for evaluating the capabilities of cutting-edge LLMs.

Generative AI technology based on Large Language Models (LLM) has been developed and applied to assist or automatically generate program codes. In this paper, we evaluate the capability of existing general LLMs for Basic Linear Algebra Subprograms (BLAS) code generation for CPUs. We use two LLMs provided by OpenAI: GPT-4.1, a Generative Pre-trained Transformer (GPT) model, and o4-mini, one of the o-series of Reasoning models. Both have been released in April 2025. For the routines from level-1 to 3 BLAS, we tried to generate (1) C code without optimization from routine name only, (2) C code with basic performance optimizations (thread parallelization, SIMD vectorization, and cache blocking) from routine name only, and (3) C code with basic performance optimizations based on Fortran reference code. As a result, we found that correct code can be generated in many cases even when only routine name are given. We also confirmed that thread parallelization with OpenMP, SIMD vectorization, and cache blocking can be implemented to some extent, and that the code is faster than the reference code.

Efficient experiment reproduction is critical to accelerating progress in artificial intelligence. However, the inherent complexity of method design and training procedures presents substantial challenges for automation. Notably, reproducing experiments often requires implicit domain-specific knowledge not explicitly documented in the original papers. To address this, we introduce the paper lineage algorithm, which identifies and extracts implicit knowledge from the relevant references cited by the target paper. Building on this idea, we propose AutoReproduce, a multi-agent framework capable of automatically reproducing experiments described in research papers in an end-to-end manner. AutoReproduce enhances code executability by generating unit tests alongside the reproduction process. To evaluate the reproduction capability, we construct ReproduceBench, a benchmark annotated with verified implementations, and introduce novel evaluation metrics to assess both the reproduction and execution fidelity. Experimental results demonstrate that AutoReproduce outperforms the existing strong agent baselines on all five evaluation metrics by a peak margin of over $70\%$. In particular, compared to the official implementations, AutoReproduce achieves an average performance gap of $22.1\%$ on $89.74\%$ of the executable experiment runs. The code will be available at https://github.com/AI9Stars/AutoReproduce.

As the US tax law evolves to adapt to ever-changing politico-economic realities, tax preparation software plays a significant role in helping taxpayers navigate these complexities. The dynamic nature of tax regulations poses a significant challenge to accurately and timely maintaining tax software artifacts. The state-of-the-art in maintaining tax prep software is time-consuming and error-prone as it involves manual code analysis combined with an expert interpretation of tax law amendments. We posit that the rigor and formality of tax amendment language, as expressed in IRS publications, makes it amenable to automatic translation to executable specifications (code). Our research efforts focus on identifying, understanding, and tackling technical challenges in leveraging Large Language Models (LLMs), such as ChatGPT and Llama, to faithfully extract code differentials from IRS publications and automatically integrate them with the prior version of the code to automate tax prep software maintenance.

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model's accuracy from 41% to 80%, surpassing the o1-series models with 3x fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm.

Source code authorship attribution is important in software forensics, plagiarism detection, and protecting software patch integrity. Existing techniques often rely on supervised machine learning, which struggles with generalization across different programming languages and coding styles due to the need for large labeled datasets. Inspired by recent advances in natural language authorship analysis using large language models (LLMs), which have shown exceptional performance without task-specific tuning, this paper explores the use of LLMs for source code authorship attribution. We present a comprehensive study demonstrating that state-of-the-art LLMs can successfully attribute source code authorship across different languages. LLMs can determine whether two code snippets are written by the same author with zero-shot prompting, achieving a Matthews Correlation Coefficient (MCC) of 0.78, and can attribute code authorship from a small set of reference code snippets via few-shot learning, achieving MCC of 0.77. Additionally, LLMs show some adversarial robustness against misattribution attacks. Despite these capabilities, we found that naive prompting of LLMs does not scale well with a large number of authors due to input token limitations. To address this, we propose a tournament-style approach for large-scale attribution. Evaluating this approach on datasets of C++ (500 authors, 26,355 samples) and Java (686 authors, 55,267 samples) code from GitHub, we achieve classification accuracy of up to 65% for C++ and 68.7% for Java using only one reference per author. These results open new possibilities for applying LLMs to code authorship attribution in cybersecurity and software engineering.

Large Language Models (LLMs) have shown promising performance in code generation. However, how to reliably evaluate code generated by LLMs remains an unresolved problem. This paper presents CodeJudge, a code evaluation framework that leverages LLMs to evaluate the semantic correctness of generated code without the need for test cases. We investigate different ways to guide the LLM in performing "slow thinking" to arrive at an in-depth and reliable evaluation. We experimented with four LLMs as evaluators on four code generation datasets and five programming languages. The results show that CodeJudge significantly outperformed existing methods in most settings. Furthermore, compared with a SOTA GPT-3.5-based code evaluation method, CodeJudge achieved better results even when using a much smaller model, Llama-3-8B-Instruct. Our code and datasets are available on GitHub https://github.com/VichyTong/CodeJudge.

The advent of large language models (LLMs) has greatly facilitated code generation, but ensuring the functional correctness of generated code remains a challenge. Traditional validation methods are often time-consuming, error-prone, and impractical for large volumes of code. We introduce CodeSift, a novel framework that leverages LLMs as the first-line filter of code validation without the need for execution, reference code, or human feedback, thereby reducing the validation effort. We assess the effectiveness of our method across three diverse datasets encompassing two programming languages. Our results indicate that CodeSift outperforms state-of-the-art code evaluation methods. Internal testing conducted with subject matter experts reveals that the output generated by CodeSift is in line with human preference, reinforcing its effectiveness as a dependable automated code validation tool.