12 papers
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Dixi Yao, Tahseen Rabbani, Manzil Zaheer +1
We propose a federated learning-like framework, Federation over Text (FoT), that enables multiple clients solving different tasks to collectively generate a shared library of metac…
Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems
Zongwei Wang, Min Gao, Hongzhi Yin +5
Large language model-empowered agentic recommender systems (ARS) reformulate recommendation as a multi-turn interaction between a recommender agent and a user agent, enabling itera…
A Survey of Continual Reinforcement Learning
Chaofan Pan, Xin Yang, Yanhua Li +4
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field…
Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data
Yujie Li, Xiangkun Wang, Xin Yang +3
Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requir…
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Xuemei Cao, Hanlin Gu, Xin Yang +4
Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, w…
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
Guannan Lai, Yujie Li, Xiangkun Wang +3
Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catast…