Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containmen...
Yao Huang, Yichi Zhang, Yifan Wang et al.· 0 citations
Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choice affects how retrieval history is maintained, what context each model call receives, and what information must be re-retrieved in follow-up questions. We compare three designs: skill-based retrieval in the mai...
Karthik Ravula, Sathwik Kowtha, Rishabh Verma et al.· 0 citations
Goal interpretation is to translate a natural language instruction into a formal symbolic goal that a planner can execute. It is critical for embodied agents because any error here propagates to every downstream planning and action step. Doing it well requires both generating suitable candidates and reliably selecting...
The domain of a fine-tune trained on a previously unseen dataset is recoverable well above chance from gray-box activations and black-box outputs, and activations and outputs were more informative than the weight-delta statistics.
Shivesh Rane· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces FINCOSMOS, an open-world evaluation paradigm for agents doing financial work, and shows how an agent with persistent memory learned all ten tasks with FINCOSMOS feedback.
Yupeng Cao, Xue-Qing Peng, Ling-Fei Qian et al.· 0 citations
Results show that how information is represented to an agent shapes both its cost and its success, making the environment worth optimizing in addition to the parameters and the harness, making the environment worth optimizing in addition to the parameters and the harness.
Ming-Xuan Li, Huan-Zhi Mao, Qiu-Yang Mang et al.· 0 citations
Close-loop evaluation is proposed, an evaluation method for deployed agents that models evaluation as performance estimation under biased raters and censored outcomes, and it requires every level's conclusion to trace back to atomic data and to be computed by versioned rules.
BlockLock is presented, which keeps shared batched prefill and pins only the numerical path of the protected request, and needs no custom kernel implementations and constrains only the protected requests.
Xiu-Yuan Qi, Pedro Reviriego, Javier Conde et al.· 0 citations
Visual-text compression renders long contexts as images and is engineered around how much of the text a vision-language model (VLM) can recover. Yet recovered text is not usable text. VLMs can transcribe the text in an image word for word and still fail to answer from it; given back their own transcript, they answer ne...
Recent studies of language evolution with neural agents often use models where agents can either speak or listen, where there are only two agents in the population, or where agents can share internal representations. These choices prevent the study of how language emerges through cultural evolution, i.e. through the cu...
Maxime Toquebiau, J\'er\^ome Botoko Ekila, Paul Van Eecke et al.· 0 citations
Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while their capacity to handle \emph{implicit concepts}, such as emotions and visual s...
Chenxi Ruan, Yihan Hou, Yu Xiao et al.· 0 citations
This paper addresses the challenges of AI ethics by proposing a structure that integrates rules, policies, and AI assistants to ensure responsible AI behavior, while comparing the proposed framework to the existing state-of-the-art guardrails.
Kristina Šekrst, Jeremy McHugh, Jonathan Rodriguez Cefalu· arXiv.org· 6 citations· ⚡2
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.
