To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG

본문 미리보기

arXiv:2606.25191v1 Announce Type: new Abstract: Multi-agent document assessment for retrieval-augmented generation is computationally expensive, driving practitioners toward smaller, deployable models whose assessment mechanisms remain poorly understood. We conduct a controlled study of training-free interventions on 7B-9B instruction-tuned models across diverse QA benchmarks, revealing a sharp dichotomy in how models benefit from assessment. For weaker baselines, the dominant mechanism is per-