ReContext
Free while signed in. Answers cite the passages they came from.
Models now support 128K context windows yet still fail to use evidence already sitting in the prompt. ReContext is a training-free inference harness for long-context reasoning that uses model-internal relevance signals to build a query-conditioned evidence pool, then replays it right before final generation while preserving the full original context.
Memory framing of context: It treats the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation, a clean cognitive analogy that drives the design.
No training, no pruning: There is no fine-tuning, no external memory, and no pruning of the original context, so the method drops into existing models without changing weights or losing information.
Consistent gains across backbones: Across eight 128K long-context datasets it improves evidence utilization on Qwen3-4B, Qwen3-8B, and Llama3-8B, taking the best average rank on all three, with public code.
Why it matters: It targets the real long-context failure, using evidence that is already present, and fixes it at inference time, a cheap and general lever for reasoning over long prompts.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack