Continually Learning Agents

Hey all, 

This is a reminder that the paper selection ends today (18:00). 

Here is the list of papers that haven't been selected by anyone yet:

• Pedagogical RL: Teaching Models to Teach Themselves from Privileged Information
• SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge
• Test-Time Training with KV Binding Is Secretly Linear Attention
• Loss Smoothing for Stable Adaptation Under Distribution Shift
• Evaluating Persistent Calibration under Evolving Model Knowledge
• Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning
• End-to-End Test-Time Training for Long Context
• Three scenarios for continual learning
• Gradient Episodic Memory for Continual Learning
• Continual Learning with Deep Generative Replay

Best,

Marius