Related papers: Scientific Algorithm Discovery by Augmenting Alpha…
The rapid advancement of large language models (LLMs) has driven the development of agentic systems capable of autonomously performing complex tasks. Despite their impressive capabilities, LLMs remain constrained by their internal knowledge…
DeepResearch agents represent a transformative AI paradigm, conducting expert-level research through sophisticated reasoning and multi-tool integration. However, evaluating these systems remains critically challenging due to open-ended…
Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic baselines. Recently, evolutionary coding agents powered by…
The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that…
Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…
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…
Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to…
Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in…
Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps,…
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on…
Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as…
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard…
The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by…
As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…
Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery. We discuss two complementary agentic systems for cosmology: \texttt{CMBEvolve}, which targets tasks with explicit…
Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill…
As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large language models (LLMs) are now evolving into LLM-based…
The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true…
Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded…
Optimization can be found in many real-life applications. Designing an effective algorithm for a specific optimization problem typically requires a tedious amount of effort from human experts with domain knowledge and algorithm design…