Paper Overview
- Field: cs.CL
- Authors: Yuyang Huang, Bobo Li, Jiajia Song, Yuzhe Ding, Chong Teng, Fei Li, Donghong Ji
- Published: 2026-09-08
- arXiv: 2609.09156
Abstract
Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim.To address this challenge, the authors argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. They propose ReCite, a decoupled agentic framework that orchestrates:
1. Location perception — contextual awareness of where the citation is needed 2. Intent-aware query planning — queries aligned with the author's argumentative intent 3. Reflective verification — checking claim-evidence consistency
Trained on synthesized reasoning trajectories, the agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that this lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.
*Auto-collected on 2026-09-10.*