# rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation

arXiv: https://arxiv.org/abs/2608.18952 · HTML: https://mlsanity.com/paper/2608.18952/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- Knowledge distillation / [Distillation for recommender systems](https://mlsanity.com/distill/distillation-for-recommender-systems/)

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

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [Reinforced Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2505.19092/) (2025)
- [TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation](https://mlsanity.com/paper/2406.10450/) (2024)
- [Large Language Model Distilling Medication Recommendation Model](https://mlsanity.com/paper/2402.02803/) (2024)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation](https://mlsanity.com/paper/2506.05069/) (2025)
- [SPRec: Self-Play to Debias LLM-based Recommendation](https://mlsanity.com/paper/2412.09243/) (2024)
- [Large Language Model Enhanced Recommender Systems: A Survey](https://mlsanity.com/paper/2412.13432/) (2024)
- [Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration](https://mlsanity.com/paper/2504.11889/) (2025)
- [Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5](https://mlsanity.com/paper/2510.04003/) (2025)
- [Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layers](https://mlsanity.com/paper/2602.17410/) (2026)
- [ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark](https://mlsanity.com/paper/2607.12946/) (2026)

## Abstract (arXiv)

Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or explaining why one item fits better than another - rather than mapping history directly to a ranked list. This reasoning, however, is expensive to repeat on every ranking request and, once produced, is typically consumed once and discarded, leaving it neither reusable across future requests nor easy to inspect or correct as user tastes drift. Our insight is that reasoning does not need to be regenerated at every call if it can instead be compressed once into a compact, structured memory that a lightweight model retrieves from. We propose rEDMRec, which distills a teacher LLM's reasoning into four typed, editable experience channels - long-term preference, short-term context, item-perception, and counterfactual hard-negative comparisons - maintained by an LLM memory controller that performs Add/Delete/Modify/Keep operations and refines entries via K-agent debate. A lightweight student LLM then ranks candidates purely by retrieving from this memory, without invoking the teacher again, decoupling online inference cost from reasoning depth. Across ML-1M, Amazon Beauty, and Steam and ten student backbones, rEDMRec improves HR@1 over zero-shot, few-shot, and RAG on every backbone, and over GraphRAG on most backbones, with Impv up to 13.3% vs. the second-best baseline on ML-1M. Channel ablations show that short-term context is the only channel that helps consistently across capacity tiers, whereas long-term, item-perception, and counterfactual contributions are capacity-dependent (and can reverse on the strongest students); debate-based memory optimization lowers bank duplication by 7.4 percentage points while raising downstream HR@1 by up to +0.029 over six optimization epochs.