7 papers
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
Yiqun Chen, Wei Yang, Erhan Zhang +14
LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely op…
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
Jinyuan Feng, Xin Yu, Yiqun Chen +5
The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, current decoding strategies fa…
Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
Yiqun Chen, Jinyuan Feng, Wei Yang +9
The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcemen…
CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning
Jinyuan Feng, Chaopeng Wei, Tenghai Qiu +2
In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has bee…
OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning
Jinyuan Feng, Zhiqiang Pu, Tianyi Hu +3
Building mixture-of-experts (MoE) architecture for Low-rank adaptation (LoRA) is emerging as a potential direction in parameter-efficient fine-tuning (PEFT) for its modular design…
MA2RL: Masked Autoencoders for Generalizable Multi-Agent Reinforcement Learning
Jinyuan Feng, Min Chen, Zhiqiang Pu +2
To develop generalizable models in multi-agent reinforcement learning, recent approaches have been devoted to discovering task-independent skills for each agent, which generalize a…