NeurIPS

Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning

Re-FORC：用于高效思维链推理的自适应奖励预测

Renos Zabounidis, Aditya Golatkar, Michael Kleinman, Alessandro Achille, Wei Xia, Stefano Soatto

机构 * AWS Agentic AI（AWS智能代理部门） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

AI总结 研究提出Re-FORC自适应奖励预测方法，通过在推理模型上训练轻量级适配器，实现早期停止无前景推理链、优化模型和思维长度选择以及自适应测试时缩放，有效提升推理效率和准确率。

Comments Accepted at ICML 2026; previously accepted as a non-archival paper at the Efficient Reasoning Workshop at NeurIPS 2025