Related papers: DISCOVERYWORLD: A Virtual Environment for Developi…
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…
Many scientific disciplines have traditionally advanced by iterating over hypotheses using labor-intensive trial-and-error, which is a slow and expensive process. Recent advances in computing, digitalization, and machine learning have…
While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined challenges. We introduce DeepScientist, a system designed to…
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…
Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment to ensure their reliability and safety. However, accurate world models often have high computational…
In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…
The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although…
In the rapidly evolving field of artificial intelligence, the ability to harness and integrate knowledge across various domains stands as a paramount challenge and opportunity. This study introduces a novel approach to cross-domain…
Extreme weather events pose escalating risks to global society, underscoring the urgent need to unravel their underlying physical mechanisms. Yet the prevailing expert-driven, labor-intensive diagnostic paradigm has created a critical…
Recent advances in large language models (LLMs) have enabled a new class of AI agents that automate multiple stages of the data science workflow by integrating planning, tool use, and multimodal reasoning across text, code, tables, and…
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal physical simulation. TDW enables simulation of high-fidelity sensory data and physical interactions between mobile agents and objects in rich 3D environments. Unique…
Recent advances in large language models (LLMs) have enabled social simulation through multi-agent systems. Prior efforts focus on agent societies created from scratch, assigning agents with newly defined personas. However, simulating…
The rapid advancement of large language models has fundamentally shifted the bottleneck in AI development from computational power to data availability-with countless valuable datasets remaining hidden across specialized repositories,…
As many of us in the information retrieval (IR) research community know and appreciate, search is far from being a solved problem. Millions of people struggle with tasks on search engines every day. Often, their struggles relate to the…
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like…
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such…
Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing research focuses on online settings, desktop environments,…
Large language models (LLMs), have shown strong potential in scientific discovery, yet existing methods still face substantial challenges in the design of research workflows and multi-role collaboration mechanisms. To mitigate these issues,…
Automatic research with Large Language Models (LLMs) is rapidly gaining importance, driving the development of increasingly complex workflows involving multi-agent systems, planning, tool usage, code execution, and human-agent interaction…
We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions or web-only queries, DRBench evaluates agents on multi-step…