BFCL-v4

Researchers introduced SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play reinforcement learning framework in which a single large language model acts as both an Environment …

A new arXiv study (2608.11552v1) finds that uncertainty quantification (UQ) methods for LLM agents do not transfer uniformly from single-turn outputs to interactive trajectories. Across five LLMs and …