SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering 事件

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering arXiv:2606.00593v1 Announce Type: new Abstract: Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answe