OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents
Research
Research News
New papers, breakthroughs and academic AI research
Kernelized Activation Steering
Research
A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings
Research
Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates
Research
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
Research
Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents
Research
TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models
Research
Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution
Research
Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems
Research
Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
Research
FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification
Research
Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
Research