Science Policy

Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic. Existing agent-memory systems (e.g., MemGPT, Zep, A-MEM) gate retrieval by content, ownership, and role, not derivation, missing a cached insi

View original ↗

MIT CSAIL researchers found that at large scales, you can often remove any single image from AI training data, every image by a given artist, or every photograph of a given person, and the generated output won’t change appreciably. At top left is an image generated by a model trained on public domain artwork created by 744 artists. The others are a sampling of images that would have been generated had any one of the

View original ↗

Scientific computing is undergoing rapid transformation as advances in artificial intelligence, heterogeneous computing, automation, and data-intensive research reshape not only computational tools but also the institutions, workforce models, and collaborative practices that support scientific discovery. This report synthesizes insights from the 2026 Workshop on Next-Generation Ecosystems for Scientific Computing, th

View original ↗

Nature Computational Science, Published online: 28 August 2026; doi:10.1038/s43588-026-01046-1 A large-scale experiment at a major machine learning conference shows that when researchers privately rank their own submissions, those rankings forecast future citations more reliably than peer-review scores.

View original ↗

A holistic approach to chemical mixtures is reshaping risk assessment emphasizing mixture testing over single compounds eliminating animal testing and advancing modeling methods. Most computational models still focus on individual chemicals and conventional mixture models like concentration addition and independent action are limited they struggle with multiple Modes of Action and often miss synergistic or antagonist

View original ↗

Background. Artificial-intelligence design tools now plan genome-scale edits, and agentic systems execute those plans with progressively less human oversight. Biosecurity controls are limited to two points: refusal guardrails at the foundation model and sequence-identity screening at the synthesiser. The design stage between them, where the plan is specified, remains governed by recommendations rather than any deploy

View original ↗

Abstract Peer review in academic research aims to ensure factual correctness and identify work of high scientific potential, but rapid submission growth has made this increasingly difficult. Here we investigate an additional measure for identifying high-impact research: authors’ rankings of their own submissions to the same artificial intelligence (AI) conference. Grounded in game-theoretic reasoning, we hypothesize

View original ↗

Long-horizon robot manipulation requires both reliable execution of individual skills and coherent sequencing over extended tasks. Most hierarchical vision-language-action (VLA) models make decisions with a single forward pass, lacking a mechanism to allocate additional computation to difficult choices. We introduce τ_0-VLA, a hierarchical robot foundation model that frames high-level subtask generation as a compute-

View original ↗

Embodied agents are increasingly used to close the gap left by end-to-end policy models, but existing harnesses remain largely open-loop, reflecting only after episodes, which cannot govern real-time physical interaction. We present Zetta, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Through three timescale-separated loops, Zet

View original ↗

Action-conditioned video world models require low-latency causal generation, but extending causal distillation to interactive world models is challenging due to the need to align discrete keyboard and continuous mouse control with temporally compressed latent chunks. ForgeWM uses a progressive four-stage recipe—domain adaptation, teacher-forced causal training, causal consistency distillation, and on-policy distribut

View original ↗

Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission Pushmeet Kohli VP for Science and Strategic Initiatives, Google DeepMind, and Chief Scientist, Google Cloud Karthik Narain Chief Product and Business Officer, Google Cloud Google AI for Public Sector Empowering an Adaptive, Responsible, Secure, and Intelligent way forward Learn more Scientists today face challenges of

View original ↗

Conjecture Machines: AI agents and the new validation bottleneck in science Over the past year, agents have transformed what it means to code. Scientific research may be next — from proposing novel hypotheses, to designing experiments, to discovering algorithms that improve on the best that humans have designed. This raises urgent questions for policymakers and science funders, the biggest being how to validate the c

View original ↗