作者位次 #4/11ACL 2026Poster· Natural Language Processing
Mitigating Context Interference for Reliable and Efficient Search Agents
Boyang XUE · Bin Wu · Shuofei Qiao · Sheng Wang · Rui Wang · Yiming Du · Hongru WANG · Jeff Z. Pan · Emine Yilmaz · Kam-Fai Wong · Aldo Lipani
摘要
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would...