RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912923138392064 |
|---|---|
| author | Ran, Kun Alaofi, Marwah Hettiachchi, Danula Ma, Chenglong Anh, Khoi Nguyen Dinh Nguyen, Khoi Vo Cherumanal, Sachin Pathiyan Rashidi, Lida Scholer, Falk Spina, Damiano Sun, Shuoqi Zendel, Oleg |
| author_facet | Ran, Kun Alaofi, Marwah Hettiachchi, Danula Ma, Chenglong Anh, Khoi Nguyen Dinh Nguyen, Khoi Vo Cherumanal, Sachin Pathiyan Rashidi, Lida Scholer, Falk Spina, Damiano Sun, Shuoqi Zendel, Oleg |
| contents | This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text
track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG
(R2RAG), a research-focused retrieval-augmented generation (RAG)
architecture composed of lightweight components that dynamically adapt the
retrieval strategy based on inferred query complexity and evidence
sufficiency. The system uses smaller LLMs, enabling operation on a single
consumer-grade GPU while supporting complex research tasks. It builds on the
G-RAG system, winner of the ACM~SIGIR~2025 LiveRAG Challenge, and extends it
with modules informed by qualitative review of outputs. R2RAG won the Best
Dynamic Evaluation award in the Open Source category, demonstrating high
effectiveness with careful design and efficient use of resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20735 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition Ran, Kun Alaofi, Marwah Hettiachchi, Danula Ma, Chenglong Anh, Khoi Nguyen Dinh Nguyen, Khoi Vo Cherumanal, Sachin Pathiyan Rashidi, Lida Scholer, Falk Spina, Damiano Sun, Shuoqi Zendel, Oleg Information Retrieval Artificial Intelligence Computation and Language This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG (R2RAG), a research-focused retrieval-augmented generation (RAG) architecture composed of lightweight components that dynamically adapt the retrieval strategy based on inferred query complexity and evidence sufficiency. The system uses smaller LLMs, enabling operation on a single consumer-grade GPU while supporting complex research tasks. It builds on the G-RAG system, winner of the ACM~SIGIR~2025 LiveRAG Challenge, and extends it with modules informed by qualitative review of outputs. R2RAG won the Best Dynamic Evaluation award in the Open Source category, demonstrating high effectiveness with careful design and efficient use of resources. |
| title | RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2602.20735 |