Publications (33)
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Jun Wang, Meng Fang, Ziyu Wan +10
In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs)…
Learning Humanoid Standing-up Control across Diverse Postures
Tao Huang, Junli Ren, Huayi Wang +6
Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems, such as fall recovery. Existing approa…
Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
Muning Wen, Jakub Grudzien Kuba, Runji Lin +4
Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning…
Settling the Variance of Multi-Agent Policy Gradients
Jakub Grudzien Kuba, Muning Wen, Yaodong Yang +5
Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL…
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
Jakub Grudzien Kuba, Ruiqing Chen, Muning Wen +4
Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortu…
Understanding and Optimizing Agentic Workflows via Shapley value
Yingxuan Yang, Bo Huang, Siyuan Qi +14
Agentic workflows have become the dominant paradigm for building complex AI systems, orchestrating specialized components, such as planning, reasoning, action execution, and reflec…
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…
Reinforcing Language Agents via Policy Optimization with Action Decomposition
Muning Wen, Ziyu Wan, Weinan Zhang +2
Language models as intelligent agents push the boundaries of sequential decision-making agents but struggle with limited knowledge of environmental dynamics and exponentially huge…
Large Sequence Models for Sequential Decision-Making: A Survey
Muning Wen, Runji Lin, Hanjing Wang +6
Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer visio…
CreativeGame:Toward Mechanic-Aware Creative Game Generation
Hongnan Ma, Han Wang, Shenglin Wang +6
Large language models can generate plausible game code, but turning this capability into \emph{iterative creative improvement} remains difficult. In practice, single-shot generatio…
Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term Estimation
Yiwei Shi, Muning Wen, Qi Zhang +3
Reinforcement Learning has revolutionized decision-making processes in dynamic environments, yet it often struggles with autonomously detecting and achieving goals without clear fe…
MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning
Ming Zhou, Ziyu Wan, Hanjing Wang +6
Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated se…
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning
Hanye Zhao, Muning Wen, Yong Yu +1
Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required training effort is unknown. E…
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evo…
PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
Huacan Chai, Zijie Cao, Maolin Ran +11
Large language models (LLMs) have achieved impressive success in single-turn function calling, yet real-world applications such as travel planning or multi-stage data analysis typi…
HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarios
Jun Wang, Jiamu Zhou, Muning Wen +7
Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior. In t…
Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
Muning Wen, Junwei Liao, Cheng Deng +3
Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, hi…
MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
Ning Li, Xiangmou Qu, Jiamu Zhou +6
Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking…
Position: Agentic AI System Is a Foreseeable Pathway to AGI
Junwei Liao, Shuai Li, Muning Wen +2
Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is sufficient to achieve Artificial General Intelligence. Instead, we…
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6
LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gi…
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Junwei Liao, Haoting Shi, Ruiwen Zhou +9
Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…
Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks
Linghui Meng, Muning Wen, Yaodong Yang +7
Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also d…
From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL
Jiaqian Wang, Yutao Qi, Wenjin Hou +2
Test-time scaling can correct difficult text-to-SQL queries, but the extra computation is normally discarded after each answer. Systems increasingly retain verified repair episodes…
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
Shangding Gu, Laixi Shi, Muning Wen +5
Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment s…
Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
Xidong Feng, Ziyu Wan, Muning Wen +4
Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reaso…
P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training
Yingxuan Yang, Huayi Wang, Muning Wen +4
In the rapidly advancing field of Large Language Models (LLMs), effectively leveraging existing datasets during fine-tuning to maximize the model's potential is of paramount import…
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…
A Survey of AI Agent Protocols
Yingxuan Yang, Huacan Chai, Yuanyi Song +11
The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation,…
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Qiqiang Lin, Muning Wen, Qiuying Peng +8
Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing the…
TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
Ruiwen Zhou, Yingxuan Yang, Muning Wen +6
Numerous large language model (LLM) agents have been built for different tasks like web navigation and online shopping due to LLM's wide knowledge and text-understanding ability. A…
PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning
Kun Hu, Muning Wen, Xihuai Wang +5
Multi-agent reinforcement learning (MARL) faces challenges in coordinating agents due to complex interdependencies within multi-agent systems. Most MARL algorithms use the simultan…
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Yingxuan Yang, Chengrui Qu, Muning Wen +5
LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance…
MARFT: Multi-Agent Reinforcement Fine-Tuning
Junwei Liao, Muning Wen, Jun Wang +1
Large Language Model (LLM)-based Multi-Agent Systems (LaMAS) have demonstrated strong capabilities on complex agentic tasks requiring multifaceted reasoning and collaboration, from…