The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation Paper • 2510.23393 • Published Oct 27 • 20
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management Paper • 2508.21433 • Published Aug 29 • 7
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management Paper • 2508.21433 • Published Aug 29 • 7
PIPer: On-Device Environment Setup via Online Reinforcement Learning Paper • 2509.25455 • Published Sep 29 • 37