3 papers
cs.CL2025
Reinforcement Mid-Training
Yijun Tian, Shaoyu Chen, Zhichao Xu +4
The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an addit…
cs.CL2025
Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
Yilong Li, Chen Qian, Yu Xia +12
Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, exis…
cs.CL2025
Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
Rennai Qiu, Chen Qian, Ran Li +9
Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently en…