对长上下文的理解和推理已成为在实际应用程序中部署大型语言模型 (LLMs) 的关键要求。尽管最近的法学硕士支持越来越长的上下文窗口,，但它们常常无法使用输入, 中已存在的相关证据，从而揭示上下文访问和有效上下文利用之间的差距。在这项工作,中，我们提出递归证据重放作为用于长上下文推理的LLM工具(RECONTEXT),，一种用于改进长上下文推理的免训练推理方法。 RECONTEXT 使用模型内部相关性信号来构建查询条件证据池，并在最终生成之前重播它，同时保留完整的原始上下文。这种递归选择过程将证据组织与答案生成分开，无需训练,外部存储器,或上下文修剪。我们还提供了基于联想记忆, 的理论分析，它将上下文描述为记忆存储,，将问题描述为检索线索,，将注意力描述为线索跟踪关联,，将重播描述为痕迹重新激活。对 8 个上下文长度为 128K 的长上下文数据集进行的实验表明，RECONTEXT 持续提高了 Qwen3-4B,、Qwen3-8B, 和 Llama3-8B, 的证据利用率，在所有三个主干上实现了最佳平均排名。代码可从此 https URL 获取。
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context Reasoning (RECONTEXT), a training-free inference method for improving long-context reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external memory, or context pruning. We also provide a theoretical analysis based on associative memory, which characterizes the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at this https URL.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)