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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%thu-pacman/chitu →
- LinkedLinked via arxiv author · 85%Yanjun Zhao →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Ruizhong Qiu →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Tianxin Wei →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Yuanchen Bei →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Zhining Liu →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Lingjie Chen →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Ismini Lourentzou →
“ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning”