Related papers: In harmony with gpt-oss
Language models like OpenAI's Generative Pre-Trained Transformers (GPT-2/3) capture the long-term correlations needed to generate text in a variety of domains (such as language translators) and recently in gameplay (chess, Go, and…
This paper studies asymptotic consensus in systems in which agents do not necessarily have self-confidence, i.e., may disregard their own value during execution of the update rule. We show that the prevalent hypothesis of self-confidence in…
The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this,…
The launch of ChatGPT at the end of 2022 generated large interest into possible applications of artificial intelligence in STEM education and among STEM professions. As a result many questions surrounding the capabilities of generative AI…
The rapid development of GenAI technologies is transforming learning, assessment, and academic production in higher education. Despite increasing student adoption, many institutions lack operational mechanisms to systematically align…
Sentiment analysis methods have become popular for investigating human communication, including discussions related to software projects. Since general-purpose sentiment analysis tools do not fit well with the information exchanged by…
Autonomous multimodal language models are rapidly evolving into web agents that can browse, click, and purchase items on behalf of users, posing a threat to display advertising designed for human eyes. Yet little is known about how these…
This paper discusses OpenAIs ChatGPT, a generative pre-trained transformer, which uses natural language processing to fulfill text-based user requests (i.e., a chatbot). The history and principles behind ChatGPT and similar models are…
We study whether state-of-the-art AI coding agents, given the same data and research question, produce the same empirical results. Deploying 150 autonomous Claude Code agents to independently test six hypotheses about market quality trends…
Generative speech enhancement (GSE) models show great promise in producing high-quality clean speech from noisy inputs, enabling applications such as curating noisy text-to-speech (TTS) datasets into high-quality ones. However, GSE models…
Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of…
Listwise rerankers based on large language models (LLM) are the zero-shot state-of-the-art. However, current works in this direction all depend on the GPT models, making it a single point of failure in scientific reproducibility. Moreover,…
With the advent of off-the-shelf intelligent home products and broader internet adoption, researchers increasingly explore smart computing applications that provide easier access to health and wellness resources. AI-based systems like…
The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset,…
In numerous settings, agents lack sufficient data to directly learn a model. Collaborating with other agents may help, but it introduces a bias-variance trade-off, when local data distributions differ. A key challenge is for each agent to…
This study investigates the efficacy of six major Generative AI (GenAI) text detectors when confronted with machine-generated content that has been modified using techniques designed to evade detection by these tools (n=805). The results…
This report presents a study on the emotional dialogue capability of ChatGPT, an advanced language model developed by OpenAI. The study evaluates the performance of ChatGPT on emotional dialogue understanding and generation through a series…
Recent advances in Generative Artificial Intelligence (GenAI) have transformed educational content creation, particularly in developing tutor training materials. However, biases embedded in AI-generated content--such as gender, racial, or…
The number of publications related to the Sustainable Development Goals (SDGs) continues to grow. These publications cover a diverse spectrum of research, from humanities and social sciences to engineering and health. Given the imperative…
A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural guidance -- together implying a monotone inverse…