8 papers
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
Haoran Ling, Yuecheng Li, Zeyu Song +5
Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes. While LLM-based agents can…
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation
Yuecheng Li, Zeyu Song, Jing Yao +3
Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID spac…
RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment
Yuecheng Li, Hengwei Ju, Zeyu Song +4
Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic hetero…
Reinforced Preference Optimization for Reasoning-Augmented Recommendations
Jingtong Gao, Zeyu Song, Chi Lu +7
Recommender systems are critical for delivering personalized content across digital platforms, and recent advances in Large Language Models (LLMs) offer new opportunities to enhanc…
TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
Anay Kulkarni, ChiaEn Lu, Dheeraj Mekala +3
Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition…
Sequential Regression for Continuous Value Prediction using Residual Quantization
Runpeng Cui, Zhipeng Sun, Chi Lu +1
Continuous value prediction plays a crucial role in industrial-scale recommendation systems, including tasks such as predicting users' watch-time and estimating the gross merchandi…