Paper · arXiv 2602.11748
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Futing Wang, Jianhao Yan, Yun Luo, Ganqu Cui, Zhi Wang, Xiaoye Qu, Yue Zhang, Yu Cheng, Tao Lin
Models require in-context exploration capabilities to scale effectively at test time, but autoregressive generation faces exponential decay in sampling long sequences, which is addressed by a length-incentivized exploration method that improves performance on both in-domain and out-of-domain tasks.
Abstract
Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine multiple reasoning hypotheses within a single continuous context. Grounded in State Coverage theory, our analysis identifies a critical bottleneck to enabling this capability: while broader state coverage requires longer reasoning trajectories, the probability of sampling such sequences decays exponentially during autoregressive generation, a phenomenon we term the ``Shallow Exploration Trap''. To bridge this gap, we propose Length-Incentivized Exploration(\method). This simple yet effective recipe explicitly encourages models to explore more via a length-based reward coupled with a redundancy penalty, thereby maximizing state coverage in two-step manner. Comprehensive experiments across different models (Qwen3, Llama) demonstrate that \method effectively incentivize in-context exploration. As a result, our method achieves an average improvement of 4.4\% on in-domain tasks and a 2.7\% gain on out-of-domain benchmarks.