explore | Grilled Cheese

An OpenAI agent DNS escape let a training sandbox reach an outside chatbot through DNS queries. See the timeline, flaws, and fixes.

#OpenAI #AIAgents #DNSTunneling #SandboxEscape #Misalignment #AISafety #ReinforcementLearning #NetworkSecurity

A new JAX-based safety RL benchmark called CRAX targets robotics and autonomous driving, running up to 200x faster than CPU-based equivalents across eight tasks and three difficulty levels. Evaluations of seven safe RL…

#robotics #reinforcementlearning #AIresearch
https://arxiv.org/abs/2606.20376

New arXiv paper proposes Spatial Credit Assignment to improve reinforcement learning for GUI agents by using screen coordinates of clicks to refine credit signals. The method helps when sampled clicks all fail by ranking…

#AI #GUI #ReinforcementLearning #AIagents
https://arxiv.org/abs/2609.36939

A new arXiv paper proposes a physics-informed multi-agent framework to coordinate patient flow across hospital departments, combining BCMP queueing topology with decentralized reinforcement…

#OpenSourceAI #MultiAgentSystems #HealthcareAI #ReinforcementLearning
https://arxiv.org/abs/2609.37022

New research shows timestep weighting plays a big role in ELBO-based reinforcement learning for flow matching models, impacting performance across noise levels. The study finds effective weighting depends…

#Robotics #AIResearch #FlowMatching #ReinforcementLearning
https://arxiv.org/abs/2609.32665

CyberWorld adapts Dreamer-style world models to autonomous cyber defense, achieving better sample efficiency than a strategy-agnostic control baseline on graph-based CyberWheel attacks.]<]minimax[>[

#Robotics #CyberSecurity #WorldModels #ReinforcementLearning
https://arxiv.org/abs/2609.31893

SWE-MILE introduces an asynchronous potential-based framework for assigning milestone-level credit in long-horizon SWE agents, deriving process supervision from workflow runtime without extra reward models. It…

#SWEAgents #ReinforcementLearning #SoftwareEngineering
https://arxiv.org/abs/2609.32631

A multi-agent reinforcement learning framework pairs threat-aware clustering with MATD3 to improve energy efficiency and safe operation of UAV aerial base stations in contested environments.

#CyberSecurity #AI #UAV #ReinforcementLearning
https://arxiv.org/abs/2609.30690

Open-source Gymnasium environment OpenHail enables joint control of electric ride-hailing fleets with a fixed observation-action interface and event-driven simulation. It models request…

#OpenSourceAI #ReinforcementLearning #RideHailing #ElectricVehicles
https://arxiv.org/abs/2609.30628

On OpenAI's "Path to Astra: critical capabilities and frontier safeguards" and 28 Sep 2026 CNBC Jensen Huang interview: Applying Bridge360 Metatheory Model lens

agericomontecillodevilla.substack.com/p/on-openais...

#aigovernance
#aisafety
#machinelearning
#reinforcementlearning
#deeplearning

How can #autonomousvehicles make decisions that are not only safe, but also human-like? This article introduces a safety-first human-like decision-making framework to bridge the gap between machine-driven precision and human-like flexibility. bit.ly/4And2Nt

#ReinforcementLearning

Hoy en [Blue Chip]: "Cómo hacemos que un modelo razone (IV): aprendizaje por refuerzo basado en recompensas verificables (RLVR)" ignaciogavilan.com/como-hacemos... #RLVR #GRPO #ReinforcementLearning #AprendizajePorRefuerzo #ModelosRazonadores #ReasoningModels #IA #AI #LLM

A new monograph offers a statistical perspective on interactive decision making, unifying bandits and reinforcement learning with function approximation under a single framework. Useful reading for…

#ReinforcementLearning #Robotics #DecisionMaking #MachineLearning
https://arxiv.org/abs/2312.16730

[Blue Chip]: "Cómo hacemos que un modelo razone (IV): aprendizaje por refuerzo basado en recompensas verificables (RLVR)" ignaciogavilan.com/como-hacemos... #RLVR #GRPO #ReinforcementLearning #AprendizajePorRefuerzo #ModelosRazonadores #ReasoningModels #IA #AI #LLM

Bridge360 Metatheory Model and the Handshake Protocol Failure Thresholds: Video overview applying Bridge3;60 Metatheory Model lens

#AIGovernance
#AISafety
#MachineLearning
#ReinforcementLearning
#DeepLearning

agericomontecillodevilla.substack.com/p/bridge360-...

The Université de Toulouse is offering a PhD position in reinforcement learning and world models for a social robot, co-supervised with Australia.

mlscientist.com/phd-reinforc...

#reinforcementlearning

What developmental architecture makes the human side of that governance loop capable of governing?: Applying Bridge360 Metatheory Model lens

agericomontecillodevilla.substack.com/p/what-devel...

#AIGovernance
#AISafety
#MachineLearning
#ReinforcementLearning
#DeepLearning