Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordi...
Lumen, the open-source model, achieves performance comparable to leading proprietary systems in both translation quality and translation-instruction following, and under an absolute 1--5 LLM-judge rubric that evaluates translation-instruction following and translation quality separately.
Hao Wang, Yang-Yang Liu, Xiao-Hu Zhao et al.· 0 citations
Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing methods can retrieve correct answers, yet often rank them poorly within a large pool of seemingly relevant candidates. Even when a correct answer is retrieved, its associat...
Zi-Yang Ling, Zi-Yi Chen, Ronald X.Xu et al.· 0 citations
Visible reasoning traces of Chinese reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether the linguistic register of reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate reasoning in Cl...
Minghan Li, Guodong Zhou· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
MakSafe is presented, a formal spatiotemporal framework for specifying and checking road vehicle safety rules through semantic zones, action-based forecasting, and trace-tree reasoning, avoiding uniform time discretization.
Maksym Labzhaniia, Julien Deantoni, Marie-Agnès Peraldi-Frati et al.· Forum on Specification and D...· 0 citations
Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance. When the utterance refers to objects in a visual scene, it is necessary to maintain and update the set of plausible referents as context accumulates, without assuming that the available information identifie...
Shun Inadumi, Lee Sangmyeong, Koichiro Yoshino· 0 citations
This work finds that gates in retrieval-critical layers are not yet aligned with relevance, and finds that Mamba's retrieval bottleneck extends beyond state capacity: even when capacity is sufficient, the delayed emergence of relevance information across depth often prevents successful retrieval.
Nir Yarden, Amit Ben Artzy, Roy Schwartz· 0 citations
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different q...
Xiaohan Wang, Haozhen Zhang, Qingyuan Liu et al.· 0 citations
This work introduces BANGLAPLAN, a benchmark of 1,000 problems across ten task families grounded in everyday life and institutions in Bangladesh, and suggests that harder problems primarily reduce plan-construction accuracy, while infeasibility detection remains more robust.
Muhamad Mas'ud, S. M. Maksudul Alam, Mohammad Jaminur Islam· 0 citations
Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However, sharing these states across architectures often requires learned translators or...
Xin Li, Mengbing Liu, Hao Jiang et al.· 0 citations
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts, and Interlock, a framework for task synthesis that represents each task as a typed completion graph is proposed...
Lin-Ji Hao, Yan-Ji He, Zi-Han Wang et al.· 0 citations
People delegate multi-step work to LLM agents and read only the reply that the agent hands back. Current evaluation scores task completion and the faithfulness of reports, and it leaves open whether the requester can understand and use the reply. We call this property reply usability and measure it with a reader model...
Yilin Jiang, Fei Tan, Xuanyu Yin et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
