5 papers
Self-Harness: Harnesses That Improve Themselves
Hangfan Zhang, Shao Zhang, Kangcong Li +5
The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit d…
Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
Hao Li, Chunjiang Mu, Jianhao Chen +5
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propos…
Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model
Jing Liang, Hongyao Tang, Yi Ma +5
Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Fin…
Multi-agent Architecture Search via Agentic Supernet
Guibin Zhang, Luyang Niu, Junfeng Fang +3
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing…
EvoFlow: Evolving Diverse Agentic Workflows On The Fly
Guibin Zhang, Kaijie Chen, Guancheng Wan +5
The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, pro…