8 papers
GAGPO: Generalized Advantage Grouped Policy Optimization
Siyuan Zhu, Chao Yu, Rongxin Yang +4
Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents of…
Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web
Xiaohang Nie, Zihan Guo, Zicai Cui +20
As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneou…
CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models
Zongkai Liu, Fanqing Meng, Lingxiao Du +4
Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing R…
MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
Fanqing Meng, Lingxiao Du, Zongkai Liu +12
DeepSeek R1, and o1 have demonstrated powerful reasoning capabilities in the text domain through stable large-scale reinforcement learning. To enable broader applications, some wor…
Rapid Learning in Constrained Minimax Games with Negative Momentum
Zijian Fang, Zongkai Liu, Chao Yu +1
In this paper, we delve into the utilization of the negative momentum technique in constrained minimax games. From an intuitive mechanical standpoint, we introduce a novel framewor…
Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
Zongkai Liu, Qian Lin, Chao Yu +4
Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, m…
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
Qian Lin, Zongkai Liu, Danying Mo +1
In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences…
Policy-regularized Offline Multi-objective Reinforcement Learning
Qian Lin, Chao Yu, Zongkai Liu +1
In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach f…