mlsanityData to 14 Oct 2026

AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation

arXiv 2605.05245 ↗First posted 4 May 2026cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only limited context can be passed to the generator. Existing controllers address parts of this problem, but typically either expand context additively, select from a fixed top-k set, or optimize relevance without explicitly repairing missing bridge facts. We propose AdaGATE, a training-free evidence controller for multi-hop RAG that frames evidence selection as a token-constrained repair problem. AdaGATE combines entity centric gap tracking, targeted micro-query generation, and a utility based selection mechanism that balances gap coverage, corroboration, novelty, redundancy, and direct question relevance. We evaluate AdaGATE on HotpotQA under clean, redundancy, and noise injected retrieval conditions. Across all three settings, AdaGATE achieves the best evidence F1 among the compared controllers, reaching 62.3% on clean data and 71.2% under redundancy injection, while using 2.6x fewer input tokens than Adaptive-k. These results suggest that explicit gap-aware repair, combined with token-efficient evidence selection, improves robustness in multi-hop RAG under imperfect retrieval. Our code and evaluation pipeline are available at https://github.com/eliguo/AdaGATE.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 11 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

10 of 11 references.

References · 10

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  5. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  6. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 265
  7. 2017Constructing Datasets for Multi-hop Reading Comprehension Across Documentscited by 190
  8. 2025Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-kcited by 21
  9. 2025AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAGcited by 8
  10. 2025Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assemblycited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
  2. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  3. 2026S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
  4. 2026Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
  5. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
  6. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
  7. 2026PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation
  8. 2026MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG