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…
Author: script
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…