AI
Q-Learning With World Models
Researchers propose a new framework called QWM that combines Q-learning with world models to improve...
AI
Expected free energy as an information constraint on the Bethe Lagrangian
Researchers have proposed an alternative formulation for active inference, a method used to select a...
AI
Can LLMs Reason in a Legally Meaningful Manner? A Small-scale Study on European Court of Human Rights Cases
Researchers have investigated whether Large Language Models (LLMs) can reason in a way that's meanin...
AI
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
Researchers have developed a system to improve the durability and trustworthiness of AI audit record...
AI
Task Specialization Fine-Tuning for Contextual Reinforcement Learning
Researchers have proposed a new approach to Contextual Reinforcement Learning (C...
AI
Token Optimization and Context Window Management in Multi-Agent AI Workflows
Researchers have developed a framework to optimize token usage and context windo...
AI
Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories
Researchers have developed a web-based tool called Graphectory Viewer for analyz...
AI
Teach and Grow: An Agent-Centered Architecture for General Robot Learning
Researchers have developed an agent-centered architecture for general robot lear...