Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
Research
Research News
New papers, breakthroughs and academic AI research
A Sharp Transition in Data Reconstruction under Differential Privacy
Research
Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
Research
Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling
Research
Simultaneous Neural Optimal Transport
Research
Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning
Research
Engineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute
Research
Regime Boundary Alignment for Evidence-Gated Question Answering
Research
Structured Latent Modeling for Supervised Multimodal Information Decomposition
Research
From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
Research
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
Research
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
Research