arXiv:2509.24239v4 Announce Type: replace-cross Abstract: Recent large language models (LLMs) have shown strong reasoning capabilities. However, a critical question remains:…
arXiv:2604.20860v1 Announce Type: cross Abstract: Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application…
arXiv:2604.20726v2 Announce Type: replace-cross Abstract: This work explores the role of prompt design and judge selection in LLM-as-a-Judge evaluations of…
arXiv:2604.20688v2 Announce Type: replace-cross Abstract: Storm surge forecasting remains a critical challenge in mitigating the impacts of tropical cyclones on…
arXiv:2604.21464v1 Announce Type: cross Abstract: Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions…
arXiv:2604.21473v1 Announce Type: cross Abstract: In the treatment of complex diseases, treatment regimens using a single drug often yield limited…
Nature Machine Intelligence, Published online: 24 April 2026; doi:10.1038/s42256-026-01214-y Tang et al. introduce MatterChat, a multimodal framework effectively integrating material…
Nature Machine Intelligence, Published online: 24 April 2026; doi:10.1038/s42256-026-01239-3 Several frameworks from different disciplines are converging on the scientific question…
Nature Machine Intelligence, Published online: 24 April 2026; doi:10.1038/s42256-026-01211-1 Collectives exhibit intrinsically different operations, resources and limitations depending on whether…
Nature Machine Intelligence, Published online: 24 April 2026; doi:10.1038/s42256-026-01228-6 Lu, Thorat and colleagues report that training AI vision systems with…
