Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structures like knowledge graphs often fall short because they rely on rigid he...
Anikait Singh, Teresa Zhang, Yoonho Lee et al.· 0 citations
This work builds LinguaGuardBench from the 1,220 labelled steps of TS-Bench AgentDojo-Traj, translating only the user instruction into German, French, Turkish, Swahili and Amharic, and keeps every tool call, observation and label byte-identical, so any change in a verdict is attributable to language alone.
On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher. We show that the consolidation does not need training: with forward passes only, the capabilities of separately tuned specialists can be aggregated into one model that is...
Bang Yang, Jia-Jun Fan, Zhao-Yu Zhu et al.· 0 citations
Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality. We show this evaluation paradigm is incomplete: it conflates memory correctness with retrieval and generation quality, producing both false positives w...
Sebastian-Antonio Toma, Jean de Kernier, Mike Ply et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models (LLMs) are increasingly used in computational social science to assign scalar scores to social and psychological constructs. However, studies use different rating scales, and whether their scores remain comparable across scale designs is understudied. To address this gap, we define and systematica...
Wonjeong Jo, Gyuwan Kim, Ming Shan Hee· 0 citations
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic techniques such as context compaction and subagent forking may produce trajectories spanning multiple sessions, creating a mismatch between th...
Yilong Xu, Minrui Xu, Xinyu Zhou et al.· 0 citations
Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate control over how strongly to reinforce the distributional changes induced by a context update. We introduce EMO, a training-free framework inspired by expectation--maximization...
Personalization of Large Language Models (LLMs) is increasingly important for user-centric applications, yet prior methods mainly adapt dense LLMs, whose polysemantic neurons, each encoding multiple unrelated concepts, hinder localizing the components behind personalization, and thus understanding and controlling it. W...
Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprietary models whose terms of service forbid training competing systems. We introduce Multi-SFT, a commercially permissive collection of 502,818 instruction-response pairs a...
Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano et al.· 0 citations
Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational commentary tone, and whether fixed actual EPS beats a manipulated consensus. Six instruction/chat checkpoint conversions from four families (0.49-7.61B ba...
Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0, and Skill Self-Play make this decision through the task, admitting tasks that look learnable and inheriting every resulting update. We identify a sele...
Hao-Yi Yang, Kshitij Mishra, Nils Lukas et al.· 0 citations
An open midtraining recipe is presented that primes base models for agentic post-training, and its effectiveness on two Nemotron models of different sizes is shown, improving robustness across agent harnesses on both models.
Soumye Singhal, Joseph Jennings, Ka-Shun Shum 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.
