cs.IRNov 12, 2026

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

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

Organizations: RMIT University, Melbourne, Australia · The University of Queensland, Brisbane, Australia

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.

Figures & tables

Explore similar work

CardsList
  1. AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

    Mar 4, 2026Zijian Chen, Xueguang Ma, Shengyao Zhuang +3Agentic RetrievalDense Retrieval

  2. Revisiting RAG Retrievers: An Information Theoretic Benchmark

    Feb 25, 2026Wenqing Zheng, Dmitri Kalaev, Noah Fatsi +5RAG EvaluationIR Evaluation