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。
Weihua Du · HaileiGong · Zhan Ling · Kang Liu · Lingfeng Shen · Xuesong Yao · Yufei Xu · Dingyuan Shi · Yiming Yang · Jiecao Chen
Miao Lu · Weiwei Sun · Weihua Du · Zhan Ling · Xuesong Yao · Kang Liu · Jiecao Chen
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing multi-turn RL pipelines suffer from degraded instruction following, excessive rollout costs, and most...