4 papers
ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents
Dawei Li, Yuguang Yao, Zhen Tan +2
Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core…
Building Safer Sites: A Large-Scale Multi-Level Dataset for Construction Safety Research
Zhenhui Ou, Dawei Li, Zhen Tan +3
Construction safety research is a critical field in civil engineering, aiming to mitigate risks and prevent injuries through the analysis of site conditions and human factors. Howe…
Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
Baixiang Huang, Zhen Tan, Haoran Wang +6
Agents based on Large Language Models (LLMs) have demonstrated strong capabilities across a wide range of tasks. However, deploying LLM-based agents in high-stakes domains comes wi…
Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models
Liangjie Huang, Dawei Li, Huan Liu +1
Large Language Models (LLMs) have demonstrated remarkable self-improvement capabilities, whereby models iteratively revise their outputs through self-generated feedback. While this…