Related papers: QUEST: Training Frontier Deep Research Agents with…
Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a…
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce…
Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…
Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data…
Real dialogues with AI assistants for solving data-centric tasks often follow dynamic, unpredictable paths due to imperfect information provided by the user or in the data, which must be caught and handled. Developing datasets which capture…
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…
Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external…
Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…
Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and empirical verification. Despite these strides, evaluating…
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…
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,…
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…
Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…
We present \textbf{QED}, an open-source multi-agent system that turns human-provided research questions into complete mathematical proofs without further human guidance. Its pipeline is designed to overcome common failures of single-query…
Frontier AI models demonstrate formidable breadth of knowledge. But how close are they to true human -- or superhuman -- expertise? Genuine experts can tackle the hardest problems and push the boundaries of scientific understanding. To…
This survey examines the rapidly evolving field of Deep Research systems -- AI-powered applications that automate complex research workflows through the integration of large language models, advanced information retrieval, and autonomous…
Advancing complex reasoning in large language models relies on high-quality, verifiable datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synthesis paradigms often face a recurring trade-off:…
The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence,…
The emergence of deep research systems presents significant capabilities in problem-solving, extending from basic queries to sophisticated research tasks. However, existing benchmarks primarily evaluate these systems as agents for web…