Recent structured RAG methods leverage tree- or graph-based reasoning structures to improve multi-hop QA. However, they face key limitations in evidence-intensive QA, where answering a question requires synthesizing information scattered across dozens or even hundreds of documents: structural rigidity, which limits adaptive reasoning expansion, and topology-ignorant evidence gathering, which prevents effective integration of evidence across different reasoning nodes. To address these issues, we propose APT-RAG, an Adaptive Planning and Topology-aware evidence gathering RAG framework. Adaptive planning dynamically expands the reasoning structure based on question dependencies and evidence requirements, while topology-aware evidence gathering improves evidence coverage through sibling evidence reuse, direct retrieval, and evidence aggregation from child nodes. We further introduce evidence-guided batched answer generation to reduce significant generation overhead in evidence-intensive QA. In the experiments on evidence-intensive QA benchmarks, APT-RAG outperforms existing structured RAG methods. Our code is available at https://github.com/hyudsl/APT-RAG.

@inproceedings{lee-etal-2026-tree,
  title = {A Tree-based {RAG} Framework for Evidence-Intensive {QA} via Adaptive Planning and Topology-Aware Evidence Gathering},
  author = {Lee, Songeun and Min, Kyungjin and Na, Injae and Suyeong, Lee and Kim, Chi-young and Jung, Woohwan},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  month = oct,
  year = {2026},
  address = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2026.findings-emnlp.1553/},
  doi = {10.18653/2026.findings-emnlp.1553},
  pages = {33056--33082}
}