arXiv:2608.14522v1 Announce Type: new Abstract: As AI systems make more morally loaded decisions across society, one response has been moral preference…
Handover of In-Context Learning State Across Session Boundaries
arXiv:2608.14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applications…
5 Python Libraries That Make Data Cleaning More Enjoyable
This article covers five Python libraries that turn tedious data cleaning into something expressive and genuinely enjoyable.
Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Support
arXiv:2608.13563v1 Announce Type: cross Abstract: Early-stage teams often lack users, time, and budget to run repeated UX studies, yet still need…
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
arXiv:2608.14441v1 Announce Type: new Abstract: Self-evolving agents improve future behavior from interaction experience, yet existing evaluations…
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
arXiv:2608.14452v1 Announce Type: new Abstract: Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated…
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
arXiv:2608.14456v1 Announce Type: new Abstract: Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the…
The Dynamics of Intelligence Explosions
arXiv:2608.14426v1 Announce Type: new Abstract: AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loop might be…
Anthropic watermarks Claude’s output, but critics question the tradeoffs
Anthropic’s text watermarking for Claude is supposed to make AI-generated content detectable. But critics doubt that word choice stays unaffected, and…
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
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,…