arxiv.orgpaperReCite: Agentic Reasoning for Faithful Citation
ReCite is a decoupled agentic framework for citation recommendation that replaces semantic-similarity retrieval with active claim-level reasoning, combining location perception, intent-aware query planning, and reflective verification to check claim-evidence consistency. Trained on synthesized reasoning trajectories, it triggers self-correction loops when retrieved candidates fail to logically support an author's claim, and the paper reports it outperforms larger generative models on strict citation accuracy.
TL;DR An agentic framework that grounds automatic citation recommendation in claim-level logical verification rather than semantic similarity, beating larger LLMs on citation accuracy.
Technologies named here
- ReCite
Techniques named here
- Claim-level reasoning for citation
- Location perception
- Intent-aware query planning
- Reflective verification with self-correction loops
Related in research