Related papers: PurpCode: Reasoning for Safer Code Generation

Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale…

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure…

Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored…

We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing…

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right,…

Large language models (LLMs) have shown great potential for automatic code generation and form the basis for various tools such as GitHub Copilot. However, recent studies highlight that many LLM-generated code contains serious security…

Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems, bypassing the effortful engagement that produces lasting understanding. We introduce a practical framework that helps…

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general…

Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks. When applying LLMs for code generation, recent works mainly focus on…

Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…

GPU kernel generation by LLMs has recently experienced rapid development, leveraging test-time scaling and reinforcement learning techniques. However, a key challenge for kernel generation is the scarcity of high-quality data, as most…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend…

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for…

Frequent cyber-attacks have elevated WebShell exploitation and defense to a critical research focus within network security. However, there remains a significant shortage of publicly available, well-categorized malicious-code datasets…