5 papers
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…
The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
Yiqun Zhang, Hao Li, Chenxu Wang +11
Proprietary giants are increasingly dominating the race for ever-larger language models. Can open-source, smaller models remain competitive across a broad range of tasks? In this p…
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
Jianhao Chen, Zishuo Xun, Bocheng Zhou +8
This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-vo…
Nature-Inspired Population-Based Evolution of Large Language Models
Yiqun Zhang, Peng Ye, Xiaocui Yang +5
Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction. Inspired by this principle, this paper formall…
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…