reasoning-optimization

GrowPage is an on-demand KV budgeting framework that dynamically manages cache capacity to enhance the efficiency of LLM reasoning serving, achieving a superior performance-throughput trade-off over existing methods.

ParaTempo is a training-free asynchronous parallel reasoning framework that uses temporal confidence to dynamically manage reasoning branches, reducing latency and token usage while maintaining accuracy in mathematical and scientific reasoning benchmarks.

Introduces Thoughts-as-Planning, a framework that models chain-of-thought optimization as sequential decision-making using latent world models and reinforcement learning, outperforming existing methods in efficiency and generalization.