Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents Paper • 2610.33956 • Published 23 days ago • 36
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks Paper • 2610.11794 • Published Oct 8 • 38
Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search Paper • 2608.15669 • Published Aug 16 • 64
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment Paper • 2605.06702 • Published May 5 • 3
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company Paper • 2604.22446 • Published Apr 24 • 102
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning Paper • 2306.07541 • Published Jun 13, 2023 • 2