auto_swarm_mt — Report Generation Task

Document collection: ['English subset', 'Arabic subset', 'Chinese subset', 'Russian subset']
Machine translation of documents: ['Yes we used the organizer-provided machine translations']
Write a short description of your retrieval process: Reciprocal ranked fusion over multilingual retrieval using plaid-x, multilingual LSR, and Qwen3 single dense vectors with ANN search.
Write a short description of your generation process: This run leverages the AutoGen framework. Multiple agents work on the answer generation: a query decomposition agent, document retrieval agent, report writing agent, report editing agent, and a report publishing agent. The query decomposer creates 3 queries at a time. The top 6 documents are used for fact extraction to identify key parts of documents. The report writing agent removes redundant facts. The report editing agent compiles the facts into an answer and determines whether more information is needed or the answer is ready to be published. After publishing an independent editor is used to ensure citation accuracy and fit the answer into the length limit. All generation is based on translated documents.
Which LLM(s) where used by your system?: Retrieval: XLMR and Qwen3-8B-Embedding; Generation: Llama-3.3-70B-Instruct
Open repository link: No
Assessing priority: 3