23 citations · 45 across the 15 of their papers we have counts for
19 papers
AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
Wenhao Zhou, Jiajun Song, Haitao Wang +11
Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can ex…
GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development
Xiuhui Zhang, Yi Chen, Shusheng Xu +4
Autonomous software generation (ASG) aims to turn human requirements into executable applications, but delivering these applications does not necessarily establish that their inter…
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…
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
Lu Yang, Shusheng Xu, Zhuoran Li +2
LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks…
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 Multi-Task Agentic LLMs via Two-Phase Distillation
Huaijie Wang, Shusheng Xu, Yi Wu +1
A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models by first training separate RL…
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…
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…
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…
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…
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…
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…
Native Chinese Reader: A Dataset Towards Native-Level Chinese Machine Reading Comprehension
Shusheng Xu, Yichen Liu, Xiaoyu Yi +3
We present Native Chinese Reader (NCR), a new machine reading comprehension (MRC) dataset with particularly long articles in both modern and classical Chinese. NCR is collected fro…
A Benchmark for Low-Switching-Cost Reinforcement Learning
Shusheng Xu, Yancheng Liang, Yunfei Li +2
A ubiquitous requirement in many practical reinforcement learning (RL) applications, including medical treatment, recommendation system, education and robotics, is that the deploye…
PhyloTransformer: A Discriminative Model for Mutation Prediction Based on a Multi-head Self-attention Mechanism
Yingying Wu, Shusheng Xu, Shing-Tung Yau +1
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused an ongoing pandemic infecting 219 million people as of 10/19/21, with a 3.6% mortality rate. Natural selecti…
Sequence Level Contrastive Learning for Text Summarization
Shusheng Xu, Xingxing Zhang, Yi Wu +1
Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different…
Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
Shusheng Xu, Xingxing Zhang, Yi Wu +2
Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph…