# Large Language Models are Learnable Planners for Long-Term Recommendation

arXiv: https://arxiv.org/abs/2403.00843 · HTML: https://mlsanity.com/paper/2403.00843/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 5 of 5)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Deep Reinforcement Learning for Page-wise Recommendations](https://mlsanity.com/paper/1805.02343/) (2018)
- [CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System](https://mlsanity.com/paper/2204.01266/) (2022)
- [Adap-τ: Adaptively Modulating Embedding Magnitude for Recommendation](https://mlsanity.com/paper/2302.04775/) (2023)

## Built on by (most cited first, 24 of 24)

- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations](https://mlsanity.com/paper/2502.13843/) (2025)
- [Agentic Feedback Loop Modeling Improves Recommendation and User Simulation](https://mlsanity.com/paper/2410.20027/) (2024)
- [Interactive Recommendation Agent with Active User Commands](https://mlsanity.com/paper/2509.21317/) (2025)
- [AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment](https://mlsanity.com/paper/2603.26680/) (2026)
- [Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search](https://mlsanity.com/paper/2502.00955/) (2025)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support](https://mlsanity.com/paper/2507.00535/) (2025)
- [Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale](https://mlsanity.com/paper/2511.08475/) (2025)
- [Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs](https://mlsanity.com/paper/2601.12034/) (2026)
- [Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World](https://mlsanity.com/paper/2511.00041/) (2025)
- [Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders](https://mlsanity.com/paper/2505.23053/) (2025)
- [BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models](https://mlsanity.com/paper/2601.22925/) (2026)
- [Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection](https://mlsanity.com/paper/2511.05854/) (2025)
- [Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob](https://mlsanity.com/paper/2511.16248/) (2025)
- [Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation](https://mlsanity.com/paper/2604.27747/) (2026)
- [PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams](https://mlsanity.com/paper/2606.07454/) (2026)
- [The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders](https://mlsanity.com/paper/2606.21911/) (2026)
- [UniVR: Thinking in Visual Space for Unified Visual Reasoning](https://mlsanity.com/paper/2607.12800/) (2026)
- [Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity](https://mlsanity.com/paper/2608.03272/) (2026)
- [ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents](https://mlsanity.com/paper/2609.37311/) (2026)

## Abstract (arXiv)

Planning for both immediate and long-term benefits becomes increasingly important in recommendation. Existing methods apply Reinforcement Learning (RL) to learn planning capacity by maximizing cumulative reward for long-term recommendation. However, the scarcity of recommendation data presents challenges such as instability and susceptibility to overfitting when training RL models from scratch, resulting in sub-optimal performance. In this light, we propose to leverage the remarkable planning capabilities over sparse data of Large Language Models (LLMs) for long-term recommendation. The key to achieving the target lies in formulating a guidance plan following principles of enhancing long-term engagement and grounding the plan to effective and executable actions in a personalized manner. To this end, we propose a Bi-level Learnable LLM Planner framework, which consists of a set of LLM instances and breaks down the learning process into macro-learning and micro-learning to learn macro-level guidance and micro-level personalized recommendation policies, respectively. Extensive experiments validate that the framework facilitates the planning ability of LLMs for long-term recommendation. Our code and data can be found at https://github.com/jizhi-zhang/BiLLP.