Summary
ReCite is a decoupled agentic framework for citation recommendation presented in arXiv paper 2609.09156 by researchers including Yuyang Huang and Donghong Ji. The authors argue that accurate citation requires shifting from semantic-similarity-based search to active, claim-level reasoning. While modern retrieval-augmented systems largely avoid fabricating non-existent papers, they still struggle with misattribution—citing real papers that do not logically support the author's claim. ReCite addresses this by orchestrating location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, the agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments show this lightweight framework outperforms state-of-the-art massive generative models on strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite aims to provide a reliable foundation for automated academic writing.
Paper Overview
- Research area: cs.CL (Computation and Language)
- Authors: Yuyang Huang, Bobo Li, Jiajia Song, Yuzhe Ding, Chong Teng, Fei Li, Donghong Ji
- Published: 2026-09-08
- arXiv: 2609.09156
Problem
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.Approach
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:
- Performs location perception of the claim's context
- Conducts intent-aware query planning
- Applies reflective verification of retrieved candidates
Trained on synthesized reasoning trajectories, the agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support.
Results
Experiments demonstrate that the 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.
---
*Source: arXiv:2609.09156, automatically collected on 2026-09-10.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634675