Related papers: PaT: Planning-after-Trial for Efficient Test-Time …

Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints. Existing large language model (LLM) approaches face fundamental limitations in this…

The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force sampling (for example, fixed best-of-N or self-consistency)…

Large language models (LLMs) achieve strong performance on code generation, but the mechanisms by which Chain-of-Thought (CoT) prompting helps remain unclear. We present a systematic empirical and information-theoretic study of CoT…

Utilizing large language models (LLMs) for tool planning has emerged as a promising avenue for developing general AI systems, where LLMs automatically schedule external tools (e.g., vision models) to tackle complex tasks based on task…

Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in…

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…

Testing is an integral part of the software development process. Yet, writing tests is time-consuming and therefore often neglected. Classical test generation tools such as EvoSuite generate behavioral test suites by optimizing for…

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reasoning. Common test-time scaling methods involve generating…

Automating unit test generation remains a significant challenge, particularly for complex methods in real-world projects. While Large Language Models (LLMs) have made strides in code generation, they struggle to achieve high branch coverage…

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…

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…

API testing has increasing demands for software companies. Prior API testing tools were aware of certain types of dependencies that needed to be concise between operations and parameters. However, their approaches, which are mostly done…

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. LLMs take a prompt consisting of requirement-code examples and a new requirement as input, and output new programs. Existing studies…

One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a…

Large language model (LLM) applications are increasingly executed as heterogeneous multi-stage workflows rather than isolated inference calls. In these workflow directed acyclic graphs (DAGs), scheduling decisions affect not only the…

Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation…