Related papers: Scientific Algorithm Discovery by Augmenting Alpha…
We present \textbf{Deep Researcher Agent}, an open-source framework that enables large language model (LLM) agents to autonomously conduct deep learning experiments around the clock. Unlike existing AI research assistants that focus on…
Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective…
We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind's Alpha-Evolve, was recently developed to…
Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts…
Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scale scientific…
Large language models (LLMs) have not only revolutionized natural language processing but also extended their prowess to various domains, marking a significant stride towards artificial general intelligence. The interplay between LLMs and…
Large Language Models (LLMs) have emerged as powerful operators for evolutionary search, yet the design of efficient search scaffolds remains ad hoc. While promising, current LLM-in-the-loop systems lack a systematic approach to managing…
Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges,…
The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data…
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…
Discovering the governing equations of dynamical systems is a central problem across many scientific disciplines. As experimental data become increasingly available, automated equation discovery methods offer a promising data-driven…
Algorithmic discovery has traditionally relied on human ingenuity and extensive experimentation. Here we investigate whether a prominent scientific computing algorithm, the Kalman Filter, can be discovered through an automated, data-driven,…
We introduce DeepResearch$^{\text{Eco}}$, a novel agentic LLM-based system for automated scientific synthesis that supports recursive, depth- and breadth-controlled exploration of original research questions -- enhancing search diversity…
The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web…
Large language models (LLMs) serve as an active and promising field of generative artificial intelligence and have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this…
Deep research systems powered by LLM agents have transformed complex information seeking by automating the iterative retrieval, filtering, and synthesis of insights from massive-scale web sources. However, existing systems predominantly…
Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in…
Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised…
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…
We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…