DuQUAD: dual-view agents with evidence pruning fix 'Lost in the Middle' in RAG
_reachsumit · x · 2026-10-30
A new paper proposes DuQUAD, a multi-document QA framework targeting the 'Lost in the Middle' problem in RAG:
- Dual-view reasoning mitigates positional bias: a Local Agent guided by a Structural Fusion Score recovers targeted evidence, while a Global Agent reasons over the full document set.
- Explicit quality scoring filters candidate evidence, with sentence-level refinement to cut noise from spurious documents.
- It beats the strongest Lost-in-the-Middle baselines by 3.0% accuracy on average and 9.4% gold evidence recall, while cutting compute cost versus existing multi-agent frameworks.
More from Research
- UChicago seminar: hippocampal ripples, visual imagery BCIs, minimally invasive neural interfaces — plopesresearch · 2026-10-30
- Certificate-Guided Visual Routing paper makes diffusion VLMs look only when needed — _akhaliq · 2026-10-30
- Oopsie-data: Building the first open dataset of robot failure trajectories — chris_j_paxton · 2026-10-30
- AI Agents Audit 138 Economics Papers, Flag 2,035 Potential Problems — haider1 · 2026-10-30
- Schmidhuber's 'Miraculous Year 1990-91': claiming roots of GANs, Transformers, pre-training — SchmidhuberAI · 2026-10-30
- NBER opens applications for Stanford Digital Economics and AI tutorial, due Nov 3 — avicgoldfarb · 2026-10-30