14 citations · 24 across the 16 of their papers we have counts for
17 papers
Verifiable Process Rewards for Agentic Reasoning
Huining Yuan, Zelai Xu, Huaijie Wang +6
Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet existing approaches predominantly rely on sparse…
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
Zelai Xu, Zhexuan Xu, Ruize Zhang +7
Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use.…
MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation
Lu Yang, Zelai Xu, Minyang Xie +4
Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
Chao Yu, Qixin Tan, Jiaxuan Gao +7
Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time…
EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models
Zheyue Tan, Mustapha Abdullahi, Tuo Shi +5
Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn…
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Huining Yuan, Zelai Xu, Zheyue Tan +10
Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforc…
RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment
Xiaoyang Cao, Zelai Xu, Mo Guang +4
Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human…
Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning
Ruize Zhang, Sirui Xiang, Zelai Xu +6
In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-le…
AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
Le Qiu, Zelai Xu, Qixin Tan +3
Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities…
Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
Zelai Xu, Wanjun Gu, Chao Yu +2
Large language model (LLM) agents have recently demonstrated impressive capabilities in various domains like open-ended conversation and multi-step decision-making. However, it rem…
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
Zelai Xu, Ruize Zhang, Chao Yu +9
Robot sports, characterized by well-defined objectives, explicit rules, and dynamic interactions, present ideal scenarios for demonstrating embodied intelligence. In this paper, we…
A Survey on Self-play Methods in Reinforcement Learning
Ruize Zhang, Zelai Xu, Chengdong Ma +8
Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has show…
Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games
Zelai Xu, Yancheng Liang, Chao Yu +2
Self-play (SP) is a popular multi-agent reinforcement learning (MARL) framework for solving competitive games, where each agent optimizes policy by treating others as part of the e…
Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
Zelai Xu, Chao Yu, Fei Fang +2
Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to e…
Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning
Jiayu Chen, Zelai Xu, Yunfei Li +6
Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effect…
Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
Wei Fu, Chao Yu, Zelai Xu +2
Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorith…