Metraipolis › archive › dc_d700e47afd17
ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning — arXiv:2611.11771
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11771
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:33.211Z
- SHA-256 of the archived text
19a8dbacdc4e824a0a93c837a3d491b30382f3e0d08869f7bc74cab33e1e1b02- Stable URL of this page
https://metraipolis.com/documento/dc_d700e47afd17
How to cite
ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning — arXiv:2611.11771 — arXiv (en), https://arxiv.org/abs/2611.11771 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d700e47afd17 (Metraipolis archive dc_d700e47afd17, sha256 19a8dbacdc4e824a0a93c837a3d491b30382f3e0d08869f7bc74cab33e1e1b02)
BibTeX
@misc{dcd700e47afd17,
title = {ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning — arXiv:2611.11771},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11771},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d700e47afd17; sha256 19a8dbacdc4e824a0a93c837a3d491b30382f3e0d08869f7bc74cab33e1e1b02},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11771. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-Augmented Generation (RAG) systems have demonstrated remarkable effectiveness in mitigating hallucinations by incorporating external knowledge. However, the retrieval process inevitably introduces noise, posing significant challenges to RAG robustness. Fundamentally, noise robustness is a composite competency encompassing noise identification, retrieval filtering, and robust reasoning. Unfortunately, existing methods often fail to capture this holistic nature, typically restricted to single-dimensional enhancements or hampered by noise-induced optimization interference. To address these limitations, we decompose RAG robustness into three sub-tasks: knowledge boundary perception, retrieval verification, and robust reasoning. Accordingly, we propose ARMOR, an Adaptive Curriculum Meta-Learning for Noise Robust RAG Reasoning. Inspired by the teaching process, ARMOR introduces an adaptive task scheduler as a teacher to curate training plans according to the absolute learning progress of RAG generators (Student). Distinct from GRPO, ARMOR utilizes inter-group advantage estimation during learning to effectively mitigate mode collapse caused by limited output spaces. Experiments on three complex reasoning datasets (2WikiMultiHopQA, MusiQue, and HotPotQA) indicate that ARMOR achieves synergistic improvements in retrieval noise robustness, significantly outperforming baselines in output quality. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.11771 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.522Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).