5 papers
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
Chunyu Miao, Henry Peng Zou, Yangning Li +28
Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing…
Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu +12
Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address co…
PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
Yaozu Wu, Jizhou Guo, Dongyuan Li +9
Effective guardrails are essential for safely deploying LLM-based agents in critical applications. Despite recent advances, existing guardrails suffer from two fundamental limitati…
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
Jizhou Guo
Large Language Models (LLMs) have demonstrated impressive performance across various tasks, with different models excelling in distinct domains and specific abilities. Effectively…
Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling
Jizhou Guo, Zhaomin Wu, Hanchen Yang +1
Best-of-N sampling is a powerful method for improving Large Language Model (LLM) performance, but it is often limited by its dependence on massive, text-based reward models. These…