arXiv:2609.35808v1 Announce Type: cross Abstract: Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded…
Can Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?
arXiv:2609.35809v1 Announce Type: cross Abstract: The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for…
Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning
arXiv:2609.35811v1 Announce Type: cross Abstract: Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API…
Local Predictability and Collective Fidelity in LLM-Agent Societies
arXiv:2609.35813v1 Announce Type: cross Abstract: Compact surrogates could reduce the cost of simulating large language model societies, but must…
Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain…
Alignment Forecasting: Predicting Misalignment From Training Data
arXiv:2609.35805v1 Announce Type: cross Abstract: Training a language model on data with a narrow flaw can sometimes make the model broadly misaligned.…
From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework
arXiv:2609.35806v1 Announce Type: cross Abstract: Automated skill extraction underpins workforce planning, yet most systems represent skills as flat…
Binarization Flattens the Score Space
arXiv:2609.35797v1 Announce Type: cross Abstract: Large language model (LLM) judges are often used as rewards to train policies on objectives that…
Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models
arXiv:2609.35804v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities in various natural language processing…
AI News Brief Hourly Summary 2026-10-01 04h : 10 posts
10 posts published in the last hour 01:32Bathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty 01:32Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning 01:32Calibration-First Cross-Cohort Multimodal Temporal Learning for Transferable Asthma-Risk Forecasting 01:32Sage: Formalization with Semantic Correction 01:32Learning…
Bathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty
arXiv:2601.04094v4 Announce Type: cross Abstract: Effective regulation of AI is a defining policy challenge, driven by their integration into all aspects…
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own…
Calibration-First Cross-Cohort Multimodal Temporal Learning for Transferable Asthma-Risk Forecasting
arXiv:2609.35795v1 Announce Type: cross Abstract: Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and…
Sage: Formalization with Semantic Correction
arXiv:2609.35790v1 Announce Type: cross Abstract: While neural theorem provers have achieved impressive milestones in formal mathematics, they largely…
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
arXiv:2609.38143v1 Announce Type: new Abstract: Agent performance depends on both reasoning ability and the environment in which it acts. We study…
Character Training for Risk-Averse Agents
arXiv:2609.38093v1 Announce Type: new Abstract: Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned…
Stochastic World Models for Verifying Vision-Based Neural Feedback Systems
arXiv:2609.38120v1 Announce Type: new Abstract: Verifying a vision-based neural feedback system requires a model of the observations its controller acts…
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
arXiv:2609.38142v1 Announce Type: new Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In…