Related papers: ASI-Evolve: AI Accelerates AI
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…
Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
This paper investigates the Jolting Technologies Hypothesis, which posits superexponential growth (increasing acceleration, or a positive third derivative) in the development of AI capabilities. We develop a theoretical framework and…
AI models underpin data-centric applications from image and text processing to scientific discovery in biology, physics, and chemistry. Yet developing them remains heavily manual, requiring practitioners to design architectures, build…
Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…
The AI community has been exploring a pathway to artificial general intelligence (AGI) by developing "language agents", which are complex large language models (LLMs) pipelines involving both prompting techniques and tool usage methods.…
Software automation has long been a central goal of software engineering, striving for software development that proceeds without human intervention. Recent efforts have leveraged Artificial Intelligence (AI) to advance software automation…
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI…
Effective human-AI collaboration for physical task completion has significant potential in both everyday activities and professional domains. AI agents equipped with informative guidance can enhance human performance, but evaluating such…
Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs significant environmental, economic, and ethical costs,…
The role of Artificial Intelligence (AI) in education is undergoing a rapid transformation, moving beyond its historical function as an instructional tool towards a new potential as an active participant in the learning process. This shift…
AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond…
Traditional self-adaptive systems automatically reconfigure existing components in response to changing requirements, but provide limited support for the generation of novel functionalities. The software generation capabilities of large…
The rapid advancement of AI has changed the character of HPC usage such as dimensioning, provisioning, and execution. Not only has energy demand been amplified, but existing rudimentary continual learning capabilities limit ability of AI to…
Lifelong learning - an agent's ability to learn throughout its lifetime - is a hallmark of biological learning systems and a central challenge for artificial intelligence (AI). The development of lifelong learning algorithms could lead to a…
The field of Artificial Intelligence (AI) and, in particular, the Machine Learning area, counts on a wide range of performance metrics and benchmark data sets to assess the problem-solving effectiveness of its solutions. However, the…
Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic…
Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significant advances in automating aspects of scientific reasoning,…
Recent advances in AI agents for software engineering and scientific discovery have demonstrated remarkable capabilities, yet their application to developing novel ranking models in commercial search engines remains unexplored. In this…