Category
8,786 papers
Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line of work therefore has agents carry a short written state instead: at every step a writer rewrites the state, and a reader acts from the state alone. Steps stay cheap, but...
One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebuild from the original problem. Grounding an inspector agent in that problem is worth +0.608 [+0.517, +0.700] to +0.358 over a blind one on four open-weight backbones serv...
CLAIRE (Clinical Language and Agentic Intelligence for Reasoning and Entry), a hybrid workflow that separates field-state discovery, source-to-field mapping, deterministic validation, bounded correction, escalation, and audit tracing, is developed and evaluated.
The Adaptive Consistency Graph (ACG) is introduced, which incrementally organizes execution evidence and its provenance in a persistent graph, then constructs a temporary requirement-centered view for each decision under a bounded context budget.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Auditing publicly released descendants of distilled models spanning diverse post-training objectives, SCOUT consistently identifies the distillation source and tracing teacher-associated *syntactic signatures* along training trajectories reveals that they emerge during distillation and persist through subsequent prefer...
MALA, a fused attention primitive that preserves score access to every legal causal interaction and uses normalized contribution to allocate post-score computation, indicates that allocating post-score computation according to normalized attention contributions can retain the evaluated capabilities of FullAttn while re...
It is found that model pairs can learn to communicate the secret using only one bit of feedback indicating whether the receiver inferred it correctly, during inference with fixed parameters and no supplied codebook or encoding examples.
Information-Gain-Gated Self-Distillation (IGSD) is proposed, which verifies on-policy token proposals with environment feedback before distillation, and supports environment-verified hindsight as an effective approach to reliable action-level supervision for search agents.
CUE-Mem provides a testbed for memory systems that selectively retain, retrieve, and use subtle multimodal evidence, and provides a testbed for memory systems that selectively retain, retrieve, and use subtle multimodal evidence.
This work introduces PULSE (Paired Utility Localization over Sparse Encodings), an SAE-based framework for identifying model-internal features associated with demonstration utility and using them for demonstration selection, and PULSE-Retriever, which converts its magnitude into a feature-relevance mask for scalable po...
ForkLeft, a distillation framework that resolves a fundamental mismatch between autoregressive teacher predicts from a left prefix and NTP teacher under the same context, is introduced, showing that DLMs can learn NTP-style reasoning without sacrificing native parallel generation.
Agentsensus, a story-world simulation framework in which there is an unified long-term memory, is presented and is the only design whose memory becomes shared and linked, at judged simulation quality indistinguishable or even better than the baselines.
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.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
