10 posts published in the last hour
- 04:32Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
- 04:32Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration
- 04:32XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
- 04:32The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents
- 04:32Decision-Focused Active Learning for Scale-Aware Critical-Materials Recovery
- 04:03An Autonomous GeoAI Agent for Arctic Eco-Navigation
- 04:03OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows
- 04:02Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
- 04:02Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions
- 04:02Adaptive Entangled Game Modules in Artificial General Intelligence