Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomiz...
Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Models (GRMs). However, Mix-RL suffers from two critical bottlenecks: the reward sparsity induced by outcome rewards, and the cross-domain interference arising from jointly o...
Qing-Lin Su, Li-Cheng Pan, Zhen Fang et al.· 0 citations
Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of structurally distinct replacement molecules represent two fundamentally different search problems. LLM-based molecular design agents typically perform the former, conducti...
Yanyi Su, Chenyan Wang, Yulei Gong et al.· 0 citations
LLMs absorb vast knowledge from training data, yet their inherently probabilistic nature offers no guarantee that this knowledge will surface in their outputs. To bridge this gap, Knowledge Extraction Enhancement (KEE) techniques such as activation steering, decoding adjustments, and prompting modify inference, potenti...
Minsuh Joo, Youna Kim, Choonghyun Park et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation, and introduces privileged disagreement correction to explicitly suppress locally overvalued actions.
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also penalizes margin expansions. We ask whether a soft auxiliary can preserve selected local non-target margin relations without freezing that dis...
Yuxuan Wang, Guangxiang Zhao, Xinyu Tan et al.· 0 citations
Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2 reasoning capacity, is a promising alternative if built at the scale of LLMs; howeve...
Xiaocong Yang, Xuanyu Meng, Yuji Zhang et al.· 0 citations
This work reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations, and introduces Precog-RM, a transformer-based model that meta-learns a representation in which outcome prediction can be performed in a few-shot setting.
Alexander Gill, Guram Gogia, F. Guzmán· 0 citations
Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates this issue, low-bit quantization (e.g., 2-bit) severely degrades model accuracy. Recent mixed-precision key-cache quantization methods mitigate this degradation by allocat...
CALIF is a lightweight method that augments verifier rewards with a calibrated likelihood-based bonus to preserve response quality and outperforms corresponding base policies in 40 of 45 model-metric comparisons across three rubric-based instruction-following benchmarks.
Sangyeon Yoon, Wooseok Seo, Hamish Ivison et al.· 0 citations
Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tasks that require multiple interactions, rewards are given only upon successful task completion, making all-fail groups common early in training and limiting opportunities...
Minchan Kim, Sungho Bae, Young-Jin Kim et al.· 0 citations
A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those regions, so a gate-versus-random comparison does not isolate these mechanisms. We introduce Counterfactual Gate-Support Decomposition (CGSD), a four-arm, budget-matched de...
Hyojung Han, Jongmin Kim, Seung-Hun Jeon· 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.
