Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-retrieval knowledge-point in...
Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dead-end trajectories. Agents must therefore be able to proactively recover from such states and turn their exploratory experience into guidance for subsequent decisions....
Ziang Ye, Wentao Shi, Lei Chen et al.· 0 citations
Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, existing work remains largely confined to non-embodied settings, without extending to embodied environments. To address this gap, we introduce EmbodiedCLBench, the first ben...
Jie Huang, Ya-Nan Chen, Rui-Xun Liu et al.· 0 citations
Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsupervised representation trained on patent text can recover relevant connections that code-restricted search cannot, and if hyperbolic space helps. We trained a hyperbolic...
Sujith Subramanian, P N Bhargav Teja, Susen Sarkar et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents against psychologically grounded, resistant buyer personas. Existing task-oriented dialogue benchmarks assume cooperative users and measure task completion; SmartSalesBench i...
P. N. Bhargav Teja, Velpula Lokesh Reddy, Madhu Basumata et al.· 1 citation
VEPA is introduced, a framework for the verified evolution of formal agent guardrails that represents the guardrail as a formal policy of executable symbolic rules over typed agent events and consistently outperforms baselines while expanding the scope of deterministic formal-policy enforcement.
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi et al.· 0 citations
Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and luck. We introduce SpireBench, in which models play the complete comm...
A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates. This paper consolidates two research lines that address these on the same residual stream: a conditi...
Ziyang Luo, Zhong-Yao Chu, Xin-Jie He et al.· 0 citations
As LLM-powered scams proliferate, black-box forensics for conversational LLM agents offers a path to accountability for systems hidden behind anonymous endpoints. Identifying the base model behind a chatbot endpoint (attribution), without model parameter access or knowledge of the hidden system prompt, would let invest...
Isadora White, Yasaman Jafari, Taylor Berg-Kirkpatrick· 0 citations
Wearable devices capture physiological and behavioral data with increasing fidelity, but the psychological context shaping these outcomes is difficult to recover from sensor data alone, limiting the utility of passive sensing for digital health goals such as early detection of distress, personalized intervention, and t...
Tamunotonye Harry, Johanna Hidalgo, Matthew Price et al.· 0 citations
EvoRubric is proposed, a co-evolutionary RL framework that combines criterion-validity feedback, response discrimination, and peer agreement to learn rubrics for open-ended generation and improves over matched static and external evolving-rubric baselines across five benchmarks in Medical, Writing, and Science.
Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient because easy questions are over-sampled while hard questions remain under-explored. We propose \textbf{Uncertainty-Aware Budget Allocation (UAB)}, a concave integer optimization framework that reallocates a fixe...
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.
