CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering.

@inproceedings{yang-2026-compactrag, author = {Hao Yang and Zhiyu Yang and Xupeng Zhang and Wei Wei and Yunjie Zhang and Lin Yang}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2240--2251}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792512}, doi = {https://doi.org/10.1145/3774904.3792512} }