600 citations · 638 across the 24 of their papers we have counts for
26 papers
Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning
Zhengyang Zhang, Zijian Zhang, Jiaxuan Gao +4
Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding still executes long reasoni…
Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems
Junwu Xiong, Jiaxuan Gao, Wei Chai +10
Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrat…
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents
Ran Yan, Wei Fu, Jiale Li +21
LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally stati…
Building a Scalable, Reproducible, Evaluatable, and Closed-Loop Simulation Environment Foundation for Embodied Intelligence
Junwu Xiong, Yongjian Guo, Mingxi Luo +17
This paper presents a cloud-native simulation infrastructure framework for embodied intelligence that supports large-scale training, standardized evaluation, and simulation-based d…
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…
Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
Jiaxuan Gao, Yongjian Guo, Zhong Guan +5
The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned World Models as generative simu…
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…
AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
Jiarui Zhang, Yuchen Yang, Ran Yan +8
Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long tok…
From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
Jiaxuan Gao, Jiaao Chen, Chuyi He +3
Interactive tool-using agents must solve real-world tasks via multi-turn interaction with both humans and external environments, requiring dialogue state tracking, multi-step tool…
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…
AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs
Ran Yan, Youhe Jiang, Tianyuan Wu +7
Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a co…
Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
Jiaxuan Gao, Wei Fu, Minyang Xie +5
Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling complex, knowledge-intensive tasks by integrating external tools. Among diverse choice…
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hongzhou Lin, Hong Lu +5
Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize…
How Far Are We from Optimal Reasoning Efficiency?
Jiaxuan Gao, Shu Yan, Qixin Tan +6
Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redund…
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Wei Fu, Jiaxuan Gao, Xujie Shen +10
Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive paral…
Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
Ningyuan Yang, Jiaxuan Gao, Feng Gao +2
Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due…
On Designing Effective RL Reward at Training Time for LLM Reasoning
Jiaxuan Gao, Shusheng Xu, Wenjie Ye +6
Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve…
ICPL: Few-shot In-context Preference Learning via LLMs
Chao Yu, Qixin Tan, Hong Lu +5
Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tab…
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
Shusheng Xu, Wei Fu, Jiaxuan Gao +6
Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can b…
LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination
Jijia Liu, Chao Yu, Jiaxuan Gao +4
AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI co…
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
Zhiyu Mei, Wei Fu, Jiaxuan Gao +3
The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed system to efficiently generate and process a massive amount of data. However, existing open-s…
LAGOON: Language-Guided Motion Control
Shusheng Xu, Huaijie Wang, Jiaxuan Gao +3
We aim to control a robot to physically behave in the real world following any high-level language command like "cartwheel" or "kick". Although human motion datasets exist, this ta…
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
Chao Yu, Jiaxuan Gao, Weilin Liu +5
There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data.…
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration
Chao Yu, Xinyi Yang, Jiaxuan Gao +8
We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MA…