Related papers: MIST-RL: Mutation-based Incremental Suite Testing …

Bug reproduction is critical in the software debugging and repair process, yet the majority of bugs in open-source and industrial settings lack executable tests to reproduce them at the time they are reported, making diagnosis and…

Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these…

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data privacy concerns, which make them impractical for many real-world applications. A natural…

Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies have further employed reinforcement learning from verifiable…

Safety critical software assessment requires robust assessment against complex regulatory frameworks, a process traditionally limited by manual evaluation. This paper presents Document Retrieval-Augmented Fine-Tuning (DRAFT), a novel…

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning-intensive tasks. However, these models exhibit unexpected brittleness, often failing on simple variations of the same underlying task. Existing…

Large Language Models (LLMs) have recently been used to generate mutants in both research work and in industrial practice. However, there has been no comprehensive empirical study of their performance for this increasingly important…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g.,…

Large Language Models (LLMs) can generate plausible code, but in settings that require exact stdin/stdout behavior they frequently produce programs that compile yet fail tests, and in some cases they introduce security-sensitive patterns.…

LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutations as few-shot examples or none at all. This can result in generic low-quality mutations, missed context-specific…

Static analysis tools are essential for ensuring memory safety in Rust programs, particularly as Rust gains adoption in safety-critical domains. However, existing tools such as Rudra and MirChecker suffer from high false positive rates,…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Recent studies have proposed leveraging Large Language Models (LLMs) as information retrievers through query rewriting. However, for challenging corpora, we argue that enhancing queries alone is insufficient for robust semantic matching;…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely for the correctness of the final answer, yields substantial…