Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention Paper • 2602.03338 • Published Feb 3 • 26
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning Paper • 2505.24726 • Published May 30, 2025 • 282
Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning Paper • 2307.03692 • Published Jul 5, 2023 • 27
