MOTHRAG aims to cut costs for AI search over changing data
MOTHRAG is presented as a way to do multi-step search and reasoning when the underlying data changes often. GraphRAG, HippoRAG, RAPTOR, and trained retrievers usually need a to be rebuilt or a retriever to be trained again when the document changes. That makes fresh data expensive to use in systems that update every day.
MOTHRAG works at question time over a plain instead. Adding new data only requires making an embedding and appending it to the index, with no graph rebuild and no . In the reported test, using Llama-3.3-70B as the reader and 1,000 examples per dataset, MOTHRAG scored an average F1 score of 68.3.
The listed comparison scores were HippoRAG2 at 65.0, GraphRAG at 55.2, and RAPTOR at 50.2; MOTHRAG scored 78.1 on HotpotQA, 76.3 on 2Wiki, and 50.5 on MuSiQue. It is described as running through ordinary APIs without a GPU, using a fixed decision step over several answer paths, including direct reading, question splitting, and repeated evidence checking. Each answer also gets a proof tree so the reasoning trail can be checked.
Key points
- MOTHRAG adds new data by creating an embedding and appending it to the index.
- The main cost-saving claim is no rebuild and no .
- The reported average F1 score is 68.3, compared with 65.0 for HippoRAG2, 55.2 for GraphRAG, and 50.2 for RAPTOR.
- It is described as usable through normal APIs without a GPU.
- A proof tree is included so answers can be checked against their evidence path.