Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents Paper • 2608.21544 • Published Aug 21 • 1
CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering Paper • 2604.03750 • Published Apr 4 • 2
β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation Paper • 2607.28582 • Published Jul 30 • 25
D^2-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Paper • 2605.25893 • Published May 25 • 36
Forecasting Scientific Progress with Artificial Intelligence Paper • 2605.22681 • Published May 21 • 43