通过递归调用突破语言模型上下文限制，实现更长时序推理。
Recursive Models for Long-Horizon Reasoning
- 模型可自我调用分解任务，每个子任务所需上下文呈指数级缩小。
- 在布尔可满足性求解与围棋对局追踪中，小上下文下准确率显著提升。
- 适用于需要长期规划的智能体系统，尤其适合资源受限场景。
现代语言模型的推理受限于有限上下文，这一固有约束构成了长时程推理的根本障碍。我们提出递归模型作为克服该障碍的核心机制，允许模型在独立上下文中递归调用自身解决子任务。理论上证明：任何可计算问题均可被递归分解，使每个子任务所需活跃上下文比传统自回归模型呈指数级减少；这严格超越了仅依赖单序列处理（如摘要）的上下文管理方法。进一步将框架推广至具备任意上下文处理与控制流的现代智能体系统，并证明递归模型在此类系统中可达最优能力。实验上测试两种场景：微调预训练模型用于递归求解布尔可满足性问题，以及从零训练小型模型处理由精确博弈树搜索生成的围棋对局轨迹。两者均在小活跃上下文条件下实现长时程推理准确率提升。
原文摘要 · Abstract (English)
Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minimal realization, where the model can recursively invoke itself to solve subtasks in isolated contexts. We prove that any computable problem admits a recursive decomposition of reasoning in which each subtask requires only exponentially smaller active context than standard autoregressive models; this strictly surpasses any context management approach confined to a single sequence, such as summarization. We further generalize our framework to modern agentic systems with arbitrary context processing and control flows, and prove that recursive models can achieve optimal power within this broader class. Experimentally, we test two settings: fine-tuning a pretrained base model for recursive SAT solving, and training a small model from scratch on Go traces generated by exact game-tree search. Both show improved long-horizon accuracy with small active contexts.
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。