# High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning

arXiv: https://arxiv.org/abs/2602.07333 · HTML: https://mlsanity.com/paper/2602.07333/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Reinforcement learning based recommender systems: A survey](https://mlsanity.com/paper/2101.06286/) (2021)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Text Is All You Need: Learning Language Representations for Sequential Recommendation](https://mlsanity.com/paper/2305.13731/) (2023)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [GenRec: Large Language Model for Generative Recommendation](https://mlsanity.com/paper/2307.00457/) (2023)
- [RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation](https://mlsanity.com/paper/2312.16018/) (2023)
- [CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendation](https://mlsanity.com/paper/2405.02429/) (2024)
- [Embedding in Recommender Systems: A Survey](https://mlsanity.com/paper/2310.18608/) (2023)
- [LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation](https://mlsanity.com/paper/2506.21579/) (2025)
- [HiD-VAE: Interpretable Generative Recommendation via Hierarchical and Disentangled Semantic IDs](https://mlsanity.com/paper/2508.04618/) (2025)
- [End-to-end Training for Recommendation with Language-based User Profiles](https://mlsanity.com/paper/2410.18870/) (2024)
- [DV365: Extremely Long User History Modeling at Instagram](https://mlsanity.com/paper/2506.00450/) (2025)
- [TEARS: Textual Representations for Scrutable Recommendations](https://mlsanity.com/paper/2410.19302/) (2024)
- [Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat](https://mlsanity.com/paper/2504.21838/) (2025)
- [Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation](https://mlsanity.com/paper/2502.02327/) (2025)
- [A Scalable and Efficient Signal Integration System for Job Matching](https://mlsanity.com/paper/2507.09797/) (2025)

## Built on by (most cited first, 1 of 1)

- [Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale](https://mlsanity.com/paper/2609.35285/) (2026)

## Abstract (arXiv)

Effective personalization on large-scale job platforms requires modeling members based on heterogeneous textual sources, including profiles, professional data, and search activity logs. As recommender systems increasingly adopt Large Language Models (LLMs), creating unified, interpretable, and concise representations from heterogeneous sources becomes critical, especially for latency-sensitive online environments. In this work, we propose a novel Reinforcement Learning (RL) framework to synthesize a unified textual representation for each member. Our approach leverages implicit user engagement signals (e.g., clicks, applies) as the primary reward to distill salient information. Additionally, the framework is complemented by rule-based rewards that enforce formatting and length constraints. Extensive offline experiments across multiple LinkedIn products, one of the world's largest job platforms, demonstrate significant improvements in key downstream business metrics. This work provides a practical, labeling-free, and scalable solution for constructing interpretable user representations that are directly compatible with LLM-based systems.