Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an RL-based training strategy via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems.

Leiden researchers Professor Daniela Kraft and Mengshi Wei have created microscopic robots that move without sensors, software, or external control. Instead, their behaviour emerges entirely from their shape and the way they interact with their environment. This class of robots opens up entirely new possibilities for biomedical applications. Inspiration to build these robots came from nature. Kraft: "Animals like worms and snakes constantly adapt their shape as they move, which helps them to navigate their environments. Macroscopic robots similarly use flexibility for their function. However, until now, microrobots were either small and rigid, or large and flexible. We wondered if we could realize small and flexible microrobots in our lab."

Neural Information Processing Systems http://nips.cc/

Thegoal targetobjectisinthefridge. 4000 steps 3. Set Table: Getabowl (see Fig.19c).

They had four primitive actions: north, south, east, and west. Multi-Floor Office is an extension of Office to multiple floors. Pick-up and put-down have the intended effect when appropriate; otherwise they do not change the state. T owers of Hanoi contains four discs of different sizes, placed on three poles. Options generated using alternative methods called primitive actions directly.

Neural Information Processing Systems http://nips.cc/