arXiv:2608.14446v1 Announce Type: new Abstract: In the current artificial intelligence-driven innovation era, the pace of knowledge growth is…
AI News Brief Hourly Summary 2026-08-17 14h : 12 posts
12 posts published in the last hour 11:33Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations 11:33The Past and Future of AI Scientists 11:33Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons 11:33AgentRewind: Recoverable Execution for Long-Horizon LLM Agents…
Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
arXiv:2608.14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after…
The Past and Future of AI Scientists
arXiv:2608.14407v1 Announce Type: new Abstract: We present a survey of the past and future of AI Scientists: machines capable of automating science. AI…
Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons
arXiv:2608.14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models…
AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
arXiv:2608.14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons.…
New policy ideas for the Intelligence Age
OpenAI funds 14 independent projects exploring new AI policy ideas to expand economic opportunity and strengthen societal resilience in the Intelligence…
LLMs Don’t Pay for the Jump
arXiv:2608.14397v1 Announce Type: new Abstract: Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction,…
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration
arXiv:2608.14355v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables the simultaneous profiling of gene expression and tissue morphology,…
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
arXiv:2608.14339v1 Announce Type: new Abstract: We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire…
ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
arXiv:2608.14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a…
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
arXiv:2608.14375v1 Announce Type: new Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which…
Designing Sustainable Federated Learning as a Service using Neural Architecture Search
arXiv:2608.14359v1 Announce Type: new Abstract: The sustainability constraints of FLaaS consumers pose significant challenges to maintaining…
AI News Brief Hourly Summary 2026-08-17 13h : 13 posts
13 posts published in the last hour 10:33Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety 10:33Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning 10:33Program-space Diffusion for Morphology-to-Transcriptomics Prediction 10:33TimeSage-EV: A Live Benchmark for Agentic Time…
Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
arXiv:2608.14306v1 Announce Type: new Abstract: This paper presents a coordination architecture for heterogeneous UAV/UGV swarms that synthesises mission…
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
arXiv:2608.14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores…
Program-space Diffusion for Morphology-to-Transcriptomics Prediction
arXiv:2608.14330v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables genome-wide gene expression profiling while preserving tissue…
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
arXiv:2608.14270v1 Announce Type: new Abstract: Time series analysis in high-stakes domains relies on recurring data releases, where new observations can…