# PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

arXiv: https://arxiv.org/abs/2606.07454 · HTML: https://mlsanity.com/paper/2606.07454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [A Multi-Agent Conversational Recommender System](https://mlsanity.com/paper/2402.01135/) (2024)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [Scim: Intelligent Skimming Support for Scientific Papers](https://mlsanity.com/paper/2205.04561/) (2022)
- [Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking](https://mlsanity.com/paper/2308.07517/) (2023)
- [Transparent and Scrutable Recommendations Using Natural Language User Profiles](https://mlsanity.com/paper/2402.05810/) (2024)
- [Large Language Models are Learnable Planners for Long-Term Recommendation](https://mlsanity.com/paper/2403.00843/) (2024)
- [AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems](https://mlsanity.com/paper/2505.19623/) (2025)
- [PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers](https://mlsanity.com/paper/2403.02939/) (2024)
- [Agentic Feedback Loop Modeling Improves Recommendation and User Simulation](https://mlsanity.com/paper/2410.20027/) (2024)
- [Towards Personalized Deep Research: Benchmarks and Evaluations](https://mlsanity.com/paper/2509.25106/) (2025)
- [SurveyAgent: A Conversational System for Personalized and Efficient Research Survey](https://mlsanity.com/paper/2404.06364/) (2024)
- [Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems](https://mlsanity.com/paper/2405.01868/) (2024)
- [Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation](https://mlsanity.com/paper/2411.02353/) (2024)
- [The Trinity of Consistency as a Defining Principle for General World Models](https://mlsanity.com/paper/2602.23152/) (2026)
- [Knowledge-Enhanced Recommendation with User-Centric Subgraph Network](https://mlsanity.com/paper/2403.14377/) (2024)
- [Research Paper Recommender System by Considering Users' Information Seeking Behaviors](https://mlsanity.com/paper/2504.02377/) (2025)
- [Discourse-Aware Scientific Paper Recommendation via QA-Style Summarization and Multi-Level Contrastive Learning](https://mlsanity.com/paper/2511.03330/) (2025)
- [Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora](https://mlsanity.com/paper/2604.24819/) (2026)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control](https://mlsanity.com/paper/2605.15963/) (2026)

## Abstract (arXiv)

Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.