7 papers
Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
Zhihang Yuan, Chengyu Yue, Long Huang +2
Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning c…
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
Litu Ou, Kuan Li, Huifeng Yin +8
Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work mainly focused on single-turn scenarios, while research on confidence in complex…
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
Kuan Li, Zhongwang Zhang, Huifeng Yin +14
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on…
WebSailor: Navigating Super-human Reasoning for Web Agent
Kuan Li, Zhongwang Zhang, Huifeng Yin +16
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on…
MiniCPM4: Ultra-Efficient LLMs on End Devices
MiniCPM Team, Chaojun Xiao, Yuxuan Li +80
This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in…
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
Haotian Chen, Zijun Song, Boye Niu +8
Tool learning, which enables large language models (LLMs) to utilize external tools effectively, has garnered increasing attention for its potential to revolutionize productivity a…