Yi Jiang, Bing Qin, Sendong Zhao, Haochun Wang, Jianbo Li, Bairui Hu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to embedding-based compression. While researchers have tried "compressing" these documents into smaller summaries or mathematical embeddings, there is a catch: the more you compress the data, the more the LLM struggles to understand it. To address this challenge, we propose ArcAligner (Adaptive recursive context Aligner), a lightweight module integrated into the language model layers to help the model better utilize highly compressed context representations for downstream generation. It uses an adaptive "gating" system that only adds extra processing power when the information is complex, keeping the system fast. Across knowledge-intensive QA benchmarks, ArcAligner consistently beats compression baselines at comparable compression rates, especially on multi-hop and long-tail settings. The source code is publicly available 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.05038")
get_code_for_paper("2601.05038")
have("2601.05038")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.05038.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.05038)
Connect an agent — have() is free.