RMIT-ADM+S 团队参加 TREC 2026 RAG：研究智能体、检索器消融与开源权重模型复现
RMIT-ADM+S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication
AI 导读
RMIT-ADM+S 团队在 TREC 2026 RAG 赛道（ClimbMix 语料）提交了 7 个研究智能体运行结果，分别使用 OpenAI 专有模型和开源权重模型，探索不同检索策略、写作模型与智能体工作流。
正文 · 原文
Abstract: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.
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| ACM classes: | H.3.3; I.2.7 |
| Cite as: | arXiv:2611.16425 [cs.IR] |
| (or arXiv:2611.16425v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16425 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Oleg Zendel [view email]
[v1]
Thu, 12 Nov 2026 07:34:28 UTC (4,047 KB)
来源：arXiv cs.AI · arxiv.org