通过可学习的中间接口重置，提升长链条推理在有限上下文下的成功率。
ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning
- 设计可重用的中间接口，通过写回与重置机制替代被丢弃的历史
- 在固定上下文窗口下，多个长程推理任务成功率显著提升
- 适合需要持续推理且受限于上下文长度的复杂问题求解场景
长链思维推理虽能提升复杂问题求解性能，但也带来冗余累积、上下文溢出和错误固化问题。我们指出，在有限上下文窗口下，核心瓶颈并非轨迹压缩或测试时控制，而是缺乏可复用的中间接口来替代被丢弃的历史并支持持续求解。进一步发现，以结果奖励驱动的长链强化学习存在关键失败模式：当任务未完成而上下文接近耗尽时，最终答案奖励会诱导模型提前猜测而非继续谨慎推理。为此提出 ThinkReset，一种在文本空间中实现该思想的方法。ThinkReset 显式通过接口写回与重置构建可复用的中间接口，并直接优化重置后的延续求解成功率。在多个长程推理基准上，该方法在固定上下文窗口下均实现了稳定成功率达提升。
原文摘要 · Abstract (English)
Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under bounded context windows, the core bottleneck is not trajectory compression or test-time control, but the absence of a reusable intermediate interface that can replace discarded history and support continued solving. We further identify a key failure mode of outcome-reward-driven long-chain reinforcement learning: when the model has not solved the task before the window is nearly exhausted, the final-answer reward encourages premature guessing rather than continued careful reasoning. We propose ThinkReset, a text-space instantiation of this view. ThinkReset explicitly constructs reusable intermediate interfaces through interface writeback and reset, and directly optimizes post-reset continuation success. Across multiple long-horizon reasoning benchmarks, this perspective consistently improves success rates under fixed context windows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。