multi-hop-retrieval

Moth-Retrieval presents a graph-free approach to multi-hop retrieval that outperforms graph-based systems on the HotpotQA benchmark.

SpecHop is a continuous speculation framework that accelerates multi-hop retrieval agents by maintaining multiple speculative threads and verifying predictions asynchronously, achieving up to 40% latency reduction without changing final model outputs.

LogosKG introduces a hardware-aligned framework for scalable, interpretable multi-hop retrieval on billion-edge knowledge graphs, integrating degree-aware partitioning and on-demand caching to boost efficiency without sacrificing fidelity.