Beyond Outcome Rewards: Process-Aware Optimization for Search Agents
Yiwei Dai · Hengyi Cai · Hui Wu · Yili Wang · Han Xu · Minlan Shao · Yuchen Li · Shuaiqiang Wang · Xin Wang · Yi Chang · Dawei Yin
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Yiwei Dai · Hengyi Cai · Hui Wu · Yili Wang · Han Xu · Minlan Shao · Yuchen Li · Shuaiqiang Wang · Xin Wang · Yi Chang · Dawei Yin
Yiwei Dai · Hengyi Cai · Yili Wang · Zexu Sun · Shuaiqiang Wang · Yuchen Li · Xin Wang · Yi Chang · Dawei Yin
Hui Wu · Chao Xu · Jianghui Wang · Ziqiong Liu · Dong Li · Yiwei Dai · Emad Barsoum
Embodied agents in open-ended environments such as Minecraft increasingly adopt planner–controller architectures, with large language models acting as high-level planners. While planning has advanced rapidly, control remains underexplored. Existing systems commonly rely on a monolithic policy to...
Rui Miao · Yixin Liu · Yili Wang · Xu Shen · Yue Tan · Yiwei Dai · Shirui Pan · Xin Wang
The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent interactions. While existing supervised defense methods demonstrate promising performance, they may be impra...
Minlan Shao · Zijian Zhang · Yili Wang · Yiwei Dai · Xu Shen · Xin Wang