7 citations · 17 across the 16 of their papers we have counts for
18 papers
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents
Xidong Yang, Xingyi Zhang, Wenhao Li +7
Lifelong LLM agents increasingly adapt through external learning states that store past interactions as retrievable memories or reusable skills, yet existing benchmarks rarely acco…
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Yujie Zheng, Zhuo Li, Shengtao Zhang +8
Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a…
AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
Jiehao Wu, Zixiao Huang, Wenhao Li +3
Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kernels to learn from. Second, performance…
TextAtari: 100K Frames Game Playing with Language Agents
Wenhao Li, Wenwu Li, Chuyun Shen +8
We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representa…
Agentic Episodic Control
Xidong Yang, Wenhao Li, Junjie Sheng +4
Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alleviate this via external memory m…
Learning Virtual Machine Scheduling in Cloud Computing through Language Agents
JieHao Wu, Ziwei Wang, Junjie Sheng +3
In cloud services, virtual machine (VM) scheduling is a typical Online Dynamic Multidimensional Bin Packing (ODMBP) problem, characterized by large-scale complexity and fluctuating…
Scalable Reinforcement Learning for Virtual Machine Scheduling
Junjie Sheng, Jiehao Wu, Haochuan Cui +6
Recent advancements in reinforcement learning (RL) have shown promise for optimizing virtual machine scheduling (VMS) in small-scale clusters. The utilization of RL to large-scale…
SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation
Junjie Sheng, Yanqiu Lin, Jiehao Wu +4
The Satisfiability (SAT) problem is a core challenge with significant applications in software engineering, including automated testing, configuration management, and program verif…
GraphThought: Graph Combinatorial Optimization with Thought Generation
Zixiao Huang, Lifeng Guo, Wenhao Li +6
Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new…
Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym
Junjie Sheng, Zixiao Huang, Chuyun Shen +5
The formidable capacity for zero- or few-shot decision-making in language agents encourages us to pose a compelling question: Can language agents be alternatives to PPO agents in t…
Negotiated Reasoning: On Provably Addressing Relative Over-Generalization
Junjie Sheng, Wenhao Li, Bo Jin +3
Over-generalization is a thorny issue in cognitive science, where people may become overly cautious due to past experiences. Agents in multi-agent reinforcement learning (MARL) als…
ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests
Haochuan Cui, Junjie Sheng, Bo Jin +5
With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially…
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
Junjie Sheng, Lu Wang, Fangkai Yang +9
Oversubscription is a common practice for improving cloud resource utilization. It allows the cloud service provider to sell more resources than the physical limit, assuming not al…
Obtaining Dyadic Fairness by Optimal Transport
Moyi Yang, Junjie Sheng, Xiangfeng Wang +4
Fairness has been taken as a critical metric in machine learning models, which is considered as an important component of trustworthy machine learning. In this paper, we focus on o…
VMAgent: Scheduling Simulator for Reinforcement Learning
Junjie Sheng, Shengliang Cai, Haochuan Cui +9
A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling. VMAgent is inspired by practical virtua…
Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning
Wenhao Li, Xiangfeng Wang, Bo Jin +3
When solving a complex task, humans will spontaneously form teams and to complete different parts of the whole task, respectively. Meanwhile, the cooperation between teammates will…
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition
Wenhao Li, Xiangfeng Wang, Bo Jin +2
Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning (MARL). One of the reasons is the policy changes of agents during the learning process. Some…
Learning Structured Communication for Multi-agent Reinforcement Learning
Junjie Sheng, Xiangfeng Wang, Bo Jin +5
This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology fo…