Related papers: Skill-as-Pseudocode: Refactoring Skill Libraries t…

Large language models (LLMs) have emerged as powerful tools but pose significant safety risks through harmful outputs and vulnerability to adversarial attacks. We propose SaP, short for Safety Polytope, a geometric approach to LLM safety…

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task…

We propose LangProp, a framework for iteratively optimizing code generated by large language models (LLMs), in both supervised and reinforcement learning settings. While LLMs can generate sensible coding solutions zero-shot, they are often…

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Pretrained masked language models (MLMs) require finetuning for most NLP tasks. Instead, we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are computed by masking tokens one by one. We show that PLLs…

Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-as-action paradigm of CodeAct (Wang et al., 2024a) to APE…

Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression. The growing language interpretation capabilities of Large Language Models (LLMs), including in…

Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach -- involving prompting for direct move generation -- has significant drawbacks. It relies on the…

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.…

AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer…

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation, where the goal is to generate code using APIs from private libraries. Existing approaches…

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this…

A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way…

Pre-trained Vision-Language Models (VLMs) are able to understand visual concepts, describe and decompose complex tasks into sub-tasks, and provide feedback on task completion. In this paper, we aim to leverage these capabilities to support…

Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Code retrieval aims to find relevant code snippets matching natural language queries within massive codebases, playing a vital role in software development. Recent advances leverage PLMs to bridge the semantic gap between natural language…

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…