{"paper_id":"2409.07487","title":"MoA is All You Need: Building LLM Research Team using Mixture of Agents","authors":["Sandy Chen","Leqi Zeng","Abhinav Raghunathan","Flora Huang","Terrence C. Kim"],"paper_date":"2024-09-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.07487v2","page_url":"https://thequant.space/flowcharts/moa-is-all-you-need-building-llm-research-team-using-mixtur/","scores":{"empirical_rigor":3,"math_complexity":2,"quadrant":"Philosophers"},"proposes":{"status":"available","statement":"The paper introduces a Retrieval-Augmented Generation framework called Mixture of Agents (MoA), a layered network of customized small language models that collaborate to answer questions and extract information.","quote":"In this work, we introduce a RAG framework called Mixture of Agents (MoA) and demonstrate its viability as a practical, customizable, and highly effective approach for scaling RAG applications.","summary":"Large Language Models (LLMs) research in the financial domain is particularly complex due to the sheer number of approaches proposed in literature. Retrieval-Augmented Generation (RAG) has emerged as one of the leading methods in the sector due to its inherent groundedness and data source…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The evaluation assumes that cost and speed are primary constraints for enterprise RAG deployments.","type":"execution","stated":"implied","quote":"While there are many theoretical propositions for such an architecture and even a few libraries for generally applying the structure in practice, there are limited documented studies evaluating the potential of this framework considering real business constraints such as cost and speed. Although libraries such as AIFlows, Langchain, and Microsoft Autogen enable programmatic composition of agents and LLMs, there are","support":"full"},{"assumption":"Small language models (sub‑10B parameters) can provide high quality, grounded responses at lower cost than larger models.","type":"model","stated":"implied","quote":"We find that the MoA framework, consisting of small language models (Hoffmann et al., 2022), produces higher quality and more grounded responses across various financial domains that are core to Vanguard's business while simultaneously maintaining low costs. At Vanguard, we have supported the hypothesis that smaller language models [1] are the present and future when it comes to highly efficient and accurate","support":"partial"}]},"datasets":{"status":"available","items":[{"name":"10‑K/Q filings","provider":"Vanguard internal document repository","kind":"text-news","access":"proprietary","period":null,"universe":null,"quote":"Additionally, it has RAG access to raw filings and API access to a SQL database containing analyst notes with domain-specific equations.","support":"full"},{"name":"Analyst notes with domain‑specific equations","provider":"Vanguard internal database","kind":"text-news","access":"proprietary","period":null,"universe":null,"quote":"Additionally, it has RAG access to raw filings and API access to a SQL database containing analyst notes with domain-specific equations.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"MoA produces higher quality and more grounded responses across various financial domains while maintaining low costs.","kind":"performance","quote":"We find that the MoA framework, consisting of small language models (Hoffmann et al., 2022), produces higher quality and more grounded responses across various financial domains that are core to Vanguard's business while simultaneously maintaining low costs.","support":"full"},{"finding":"The latency penalty for MoA is approximately 4.07× (or 2.24× with parallel inference) compared with the original single‑model system.","kind":"performance","quote":"The latency penalty for implementing MoA is approximately 4.07x, or 2.24x when running inference in parallel.In comparison, our original single-model system was capable of performing the 8 same operation in under three seconds.","support":"full"},{"finding":"MoA has scaled to analyzing tens of thousands of documents simultaneously.","kind":"performance","quote":"At Vanguards IMFS team, our MoA system has scaled to analyzing tens of thousands of documents simultaneously.","support":"full"},{"finding":"Compounding error occurs with single‑stream serial models but not with MoA.","kind":"theoretical","quote":"In-terestingly, we observe that the concept of ”compounding error” only occurs with a single stream of serial models and not with MoA.","support":"full"},{"finding":"MoA can operate at a fraction of the cost by utilizing open‑weight, sub‑10B parameter models.","kind":"performance","quote":"MoA is an extension of this hypothesis, as it has allowed us to operate at a fraction of the cost by utilizing open-weight, sub-10B parameter models.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":33,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:55:36Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}