EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis Paper • 2601.05808 • Published 19 days ago • 36
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting Paper • 2601.02151 • Published 23 days ago • 102
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models Paper • 2408.02632 • Published Aug 5, 2024 • 1