Related papers: AlphaResearch: Accelerating New Algorithm Discover…

Large Language Models (LLMs) excel in traditional natural language processing tasks but struggle with problems that require complex domain-specific calculations or simulations. While equipping LLMs with external tools to build LLM-based…

Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate…

Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language…

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill…

Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the…

Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for…

Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding…

Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck…

Evolve-based agent such as AlphaEvolve is one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs,…

Large language models (LLMs) excel across many natural language processing tasks but face challenges in domain-specific, analytical tasks such as conducting research surveys. This study introduces ResearchArena, a benchmark designed to…

Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into…

Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in improving LLM capabilities, its implementation remains highly…

Amongst the most common use cases of modern AI is LLM chat with web search enabled. However, no direct evaluations of the quality of web research agents exist that control for the continually-changing web. We introduce Deep Research Bench,…

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…

The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated…

We demonstrate the power of human-LLM collaboration in tackling open problems in theoretical computer science. Focusing on combinatorial optimization, we refine outputs from the FunSearch algorithm [Romera-Paredes et al., Nature 2023] to…

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up…

Recent advances in web-augmented large language models (LLMs) have exhibited strong performance in complex reasoning tasks, yet these capabilities are mostly locked in proprietary systems with opaque architectures. In this work, we propose…

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

We report new results on eight problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-agent LLM system. Bolzano orchestrates rounds of interaction between parallel prover…