AdaGATE improves evidence F1 scores on HotpotQA for multi-hop RAG under clean, redundant, and noisy conditions by framing selection as gap-aware token-constrained repair, outperforming baselines while using 2.6x fewer tokens.
Dakota Wilson
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MemToolAgent improves LLM tool-using agents via structured memory extraction from feedback and dynamic retrieval, reporting relative gains of 29%, 80%, and 17% on WorkBench, NESTFUL, and PEToolBench.
citing papers explorer
-
AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation
AdaGATE improves evidence F1 scores on HotpotQA for multi-hop RAG under clean, redundant, and noisy conditions by framing selection as gap-aware token-constrained repair, outperforming baselines while using 2.6x fewer tokens.
-
MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback
MemToolAgent improves LLM tool-using agents via structured memory extraction from feedback and dynamic retrieval, reporting relative gains of 29%, 80%, and 17% on WorkBench, NESTFUL, and PEToolBench.