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

Published
Source
arXiv
Paper number
1462
Field
RAG / Agents
arXiv ID
2611.16425

Key points

  • The team submitted seven research-agent runs using proprietary OpenAI and open-weight models to the TREC RAG track, comparing 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 evaluation, six of seven runs exceeded the track median across all three rubric/nugget collections, and the best run brief-hybrid tied the track maximum of 0.892 for Batch-1 vital coverage.
  • Hybrid retrieval used 14.4% fewer searches and 8.2% fewer processed tokens than brief-base, providing the clearest efficiency improvement.
  • 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.
  • The estimated generation cost of owa-glm5 was $0.524 per topic, far below $2.823 for sol-research-first.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)