People increasingly ask large language models (LLMs) for advice on relationship, family and management decisions, usually in a single sentence, while the dimensions that decide such questions (context, history, the people affected, religion and values, consequences) are known only to the user. We ask how far a model st...
Ahmed Abdelalim· Zenodo (CERN European Organi...· 0 citations
Large language model (LLM) agents increasingly rely on external memory to support long-term interaction, task continuity, experience reuse, and collaborative problem-solving. However, existing memory architectures often emphasize individual memory management, shared memory repositories, or predefined collaboration stra...
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Search and Rescue (SAR) robotics increasingly depends on collaborative intelligence to operate effectively in dynamic, uncertain, and time-sensitive environments. Modern SAR missions require coordinated interaction among heterogeneous robotic agents as well as structured collaboration between humans and intelligent sys...
M. I. Shuvo, Awal Ahmed Fime, Raiyan Ashraf et al.· Frontiers in Robotics and AI· 0 citations
Large language models (LLMs) can generate plausible but incorrect responses, and their ability to verify their own outputs is limited by uncertainty, shared reasoning biases, and insufficient access to independent evidence. Self-verification allows a model to inspect its own output, whereas mutual verification enables...
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
In rapidly expanding megacities across the Global South, a profound data scarcity paradox frequently prevents effective environmental monitoring and evidence driven urban planning. While severe traffic congestion generates acute localised pollution, the total absence of continuous municipal traffic counters, ubiquitous...
Benjamin M. Buhendwa, Chunsheng Fang, Ju Wang· Figshare· 0 citations
Large language models (LLMs) increasingly rely on search mechanisms to acquire external information, investigate complex questions, and support evidence-based reasoning. However, search conducted independently by a single model or agent may remain constrained by its initial query formulation, prior assumptions, and lim...
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Objectives. Observational studies report large, conflicting associations between common drugs and hip or knee replacement. We tested them in the serious adverse event (SAE) tables of randomized trials on ClinicalTrials.gov. Methods. We included randomized drug trials with at least 500 participants. A language model cla...
It is examined whether recurrent self-reflection changes social behavior in a long-horizon large-language-model agent, and whether the pattern extends across model families. The experiment comprises six matched reflective (RF)/non-reflective (NR) pairs using gpt-oss-120B and a prospectively registered three-pair replic...
Christian Lotz· Zenodo (CERN European Organi...· 0 citations
In this slide deck we dive into applications and best-practices of large language models for natural language processing for the purpose of information retrieval and text translation. The target audience are scientists in linguistics and translatology who want to work more deeply with artificial intelligence. These sli...
Oliver Welz, Robert Haase· Zenodo (CERN European Organi...· 0 citations
Three fixed open-weight large language model (LLM) configurations each forecast how a recorded two-person negotiation ended, given only what the two persons brought to it (the items, both persons' private values or priorities and, in CaSiNo, the reasons they wrote beforehand) and nothing from the negotiation itself. Th...
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.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
