作者位次 #3/6ACL 2026Findings· Findings of ACL
Context-Value-Action Architecture for Value-Driven Large Language Model Agents
TianZe Zhang · Sirui Sun · Yuhang Xie · Xin Zhang · Zhiqiang Wu · Guojie Song
摘要
Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current “LLM-as-a-judge” evaluations. By evaluating against empirical ground truth, we reveal a counter-int...