Real-Time Progress Prediction in Reasoning Language Models 事件

Real-Time Progress Prediction in Reasoning Language Models arXiv:2506.23274v4 Announce Type: replace-cross Abstract: Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal progress becomes opaque to users, making expectation management and real-time oversight difficult. In this work, we investigate whether real-time p