rule-reasoning

Tag

Cards List
#rule-reasoning

RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios

Hugging Face Daily Papers ↗ · 2026-10-14 Cached

RuleTrek 是一个多领域基准,用于评估大模型智能体在复杂多文件场景中识别、推断和应用领域规则的能力。实验显示11个前沿LLM在端到端规则推理上仅得26.97%-55.29%,暴露了显著的能力差距。

0 favorites 0 likes
← Back to home

Submit Feedback