QueryFlow paper evolves the query during multi-hop graph retrieval, gaining 8.4 points Full Recall@10
JeremyCMorgan · x · 2026-11-12
arXiv paper QueryFlow treats multi-hop evidence recovery as coupled evolution of evidence representations and query conditions, recurrently integrating query-conditioned summaries of graph context into a shared query state. Across four multi-hop QA datasets it improves macro Recall@10, Full Recall@10 and LLM-Acc by 4.98, 8.40 and 8.0 points over representative baselines—relevant for iterative retrieval agents.
More from Research
- Qwen 3.8 27B on a laptop can read model weights, replicating the Weight-Space Programming paper — dl_weekly · 2026-11-12
- Trask: Transformer weight columns are concept detectors, but many concepts remain missing — iamtrask · 2026-11-12
- Dense rewards lose to standard GRPO at matched compute, arXiv paper finds — burny_tech · 2026-11-12
- Wayve unveils Learned Safety Envelope: end-to-end trained live risk prediction for AI driving — alexgkendall · 2026-11-12
- HipKittens turns one: breaking AMD's 'CUDA moat' for a multi-silicon future — simran_s_arora · 2026-11-12
- Why world model teams pay for gameplay with inputs attached: actions are the scarce half — KnowledgeOk7634 · 2026-11-12