RCER rebuilds cross-evidence relations for iterative RAG, +3 F1 on multi-hop QA
_reachsumit · x · 2026-10-15
A new arXiv paper (2610.19398) proposes RCER, an iterative RAG method that reconstructs cross-evidence relations directly from accumulated retrieved passages:
- Inter-round relational evidence acquisition identifies entity correspondences and inferential dependencies to drive dynamic question decomposition and iterative retrieval.
- Reasoning context reconstruction builds a coherent context via joint selection of complementary passages and derivation of cross-evidence inferences.
- Cross-evidence compositional reasoning uses those inferences to establish entity correspondences and compose relations for answer derivation.
RCER outperforms the best baselines by 2.83 EM and 3.06 F1 on average across three multi-hop QA benchmarks, with superior performance on narrative and implicit reasoning tasks.
More from Research
- kalomaze argues ensembled synthetic data can cover data-scarce domains — kalomaze · 2026-10-15
- Axiom claims proof of generalized quasi-Riemann hypothesis for all Dedekind zeta functions — basedjensen · 2026-10-15
- TorchLean expands into a verified tensor programming framework with einsum and GPU execution in Lean — burny_tech · 2026-10-15
- StreamErase hits 26 FPS real-time video object erasing on a single GPU, 200x faster than prior methods — Zhuobai Dong · 2026-10-15
- Huawei's SwarmRSI: evolving agent swarms achieve recursive self-improvement in science — Qianru Meng · 2026-10-15
- Glance Forcing cuts video distillation trajectory cost from thousands of GPU-hours to one — Zhuobai Dong · 2026-10-15