Related papers: SolidCoder: Bridging the Mental-Reality Gap in LLM…

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible…

In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of…

Although people are impressed by the content generation skills of large language models, the use of LLMs, such as ChatGPT, is limited by the domain grounding of the content. The correctness and groundedness of the generated content need to…

This paper proposes a neuro-symbolic framework for G-code generation that seeks to integrate the neural generative capabilities of the GLLM method (Abdelaal et al., 2025) with formal verification via a Separation Logic (SL) prover. To…

Large language models (LLMs) have achieved substantial progress in repository-level code generation. However, solving the same repository-level task often requires multiple attempts, while existing methods still optimize each attempt in…

Programmers increasingly rely on Large Language Models (LLMs) for code generation. However, misalignment between programmers' goals and generated code complicates the code evaluation process and demands frequent switching between prompt…

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize…

``Vibe coding'' -- the practice of developing software through iteratively conversing with a large language model (LLM) -- has exploded in popularity within the last year. However, developers report key limitations including the…

Large Language Models (LLMs), particularly Code LLMs, have demonstrated impressive performance in code generation. Current research primarily focuses on the correctness of generated code, while efficiency remains less explored. Recent works…

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They…

Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text…

Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming problems due to rigid…

Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…

Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts across several coupled…

Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs.…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Chain-of-thought (CoT) has emerged as a groundbreaking tool in NLP, notably for its efficacy in complex reasoning tasks, such as mathematical proofs. However, its application in code generation faces a distinct challenge, i.e., although the…

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, the training data used to develop these models often contain a significant amount of buggy code. Yet, it remains unclear to what extent these…

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep…