跳到正文

2026arXiv搜索 Agent

RMIT-ADM+ S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication

Oleg Zendel, Kun Ran, Chenglong Ma, Nguyen Khoi Vo, Shuai Wang

arXiv preprint arXiv:2611.16425, 2026

论文 ↗

摘要

We describe the RMIT-ADM+S team’s participation in the TREC 2026 Retrieval-Augmented Generation (RAG) track using the ClimbMix corpus. We submitted seven research-agent runs using proprietary OpenAI and open-weight models, exploring different retrieval strategies, writer models, and agent workflows. Pre-submission ablations identified writer selection and adjacent-chunk expansion as the main factors affecting answer quality. In the official NIST evaluation, six of seven runs exceeded the track median across all three rubric/nugget collections. Our best-performing run, brief-hybrid, achieved the highest all-item coverage among our submissions and tied the track maximum (0.892) for Batch-1 vital coverage. Human side-by-side preferences differed across evaluation batches: the open-weight owa-glm5 led Batch 1 despite lower automated coverage, while sol-research-first led Batch 2. These findings highlight differences between automated coverage measures and human preferences, as well as the potential of lower-cost open-weight models for research-agent systems.

引用 · BibTeX
@misc{zendel2026rmit,
  title = {{RMIT-ADM+ S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication}},
  author = {Oleg Zendel and Kun Ran and Chenglong Ma and Nguyen Khoi Vo and Shuai Wang},
  howpublished = {arXiv preprint arXiv:2611.16425, 2026},
  year = {2026},
  url = {https://arxiv.org/abs/2611.16425}
}