ReContext不用训练就能让模型用上长文里的关键信息，Qwen3和Llama3上都有效，适合处理超长文档推理。
ReContext是一种无需训练的长上下文推理方法，通过模型内部相关性信号构建证据池并在生成前重放。该方法在8个长上下文数据集上测试，上下文长度达128K。实验表明，ReContext在Qwen3-4B、Qwen3-8B和Llama3-8B三个模型上均提升了证据利用率，平均排名最优。
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
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 https://github.com/Yanjun-Zhao/ReContext.