# PaperRouter-Agent: A Content-Grounded LLM Agent for Personalized Hierarchical Paper Routing

arXiv: https://arxiv.org/abs/2607.11564 · HTML: https://mlsanity.com/paper/2607.11564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora](https://mlsanity.com/paper/2506.10737/) (2025)
- [CiteSee: Augmenting Citations in Scientific Papers with Persistent and Personalized Historical Context](https://mlsanity.com/paper/2302.07302/) (2023)
- [PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers](https://mlsanity.com/paper/2403.02939/) (2024)
- [End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting](https://mlsanity.com/paper/2409.03247/) (2024)
- [Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation](https://mlsanity.com/paper/2510.19897/) (2025)
- [BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions](https://mlsanity.com/paper/2310.06111/) (2023)
- [Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models](https://mlsanity.com/paper/2503.16022/) (2025)
- [AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence](https://mlsanity.com/paper/2510.01609/) (2025)
- [Towards Open-Domain Topic Classification](https://mlsanity.com/paper/2306.17290/) (2023)
- [Hierarchical Text Classification with LLM-Refined Taxonomies](https://mlsanity.com/paper/2601.18375/) (2026)
- [Hierarchical Text Classification Using Black Box Large Language Models](https://mlsanity.com/paper/2508.04219/) (2025)
- [EvoTaxo: Building and Evolving Taxonomy from Social Media Streams](https://mlsanity.com/paper/2603.19711/) (2026)

## Abstract (arXiv)

Researchers organize the papers they collect into personal folder hierarchies in reference managers, and route each new paper into the folder where it belongs. This task differs from standard hierarchical text classification. A user's folder hierarchy is not a fixed, shared taxonomy but a private and evolving folksonomy whose folder meanings may be topical, shorthand, venue-based, or process-oriented, and are often defined by the papers already stored inside them. We formalize this setting as personalized hierarchical paper routing (PHPR): assigning an incoming paper to folders in a user-specific hierarchy without per-user training. We propose PaperRouter-Agent, a training-free LLM agent that grounds routing decisions in folder members rather than folder names alone. The agent first narrows the candidate hierarchy, retrieves folder-specific evidence, verifies fit by inspecting member papers, and incorporates similarity-gated feedback from past user rejections. A formative study on real personal libraries shows that PaperRouter-Agent raises overall Recall@1 from 0.39 to 0.61 and Recall@3 from 0.57 to 0.83, with the largest gains on organizational folders defined by metadata such as venue or year, where single-shot methods collapses (Recall@1 0.09 to 0.50). On the public LaMP-2 benchmark, the same approach improves accuracy from 44.5% to 51.5% (+9.0 macro-F1) over a single-shot baseline, while remaining low-cost for practical use.