automated-agent-design

该论文提出了一种压力测试方法，通过压力比ρ和四个可证伪探针来评估LLM智能体自身的验证器（Rationale Consistency Score）在搜索压力与预言机访问下是否仍然可靠，并揭示了验证器被博弈的失败模式。

ADIAS is a framework for automated design of agentic systems that uses issue-centric optimization, maintaining a persistent issue state across repair rounds. It outperforms the strongest baseline by 25.2% on average across five interactive benchmarks and shows consistent gains with four backbone models.