让AI学会在陌生环境里主动求助专家，不靠训练时互动
YRC-Bench: A Benchmark for Learning to Coordinate with Experts
- AI在无监督环境下学习何时该让专家接管
- 新基准测试显示，部分方法能有效识别需求助的场景
- 适合研究智能体协作与安全决策的学者
实际部署中，AI代理难免遇到超出自身能力的挑战。关键的安全机制是识别在新情境下可能失败，并将控制权交由更强大的专家系统。利用专家协助可显著提升安全性与性能。由于专家资源成本高，核心挑战在于判断何时应求助。本文探索一种新问题设定YRC-0：代理需在未接触专家的情况下，于新环境中无监督地学会与专家协作。此设定推动发展低成本、鲁棒的专家调用训练方法。为此，我们提出YRC-Bench——一个开源基准，涵盖多种环境中的YRC-0任务。该基准提供类似Gym的API、模拟专家、评估流程及主流基线实现。为解决YRC-0，我们设计验证策略，并采用提议者-验证器分解作为诊断框架，评估多种学习方法，为未来研究提供洞见。
原文摘要 · Abstract (English)
When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to recognize when it is likely to fail in a novel situation and to yield control to a more capable expert system. Leveraging such expert assistance can significantly improve safety and performance in such situations. Since expert assistance is costly, a central challenge is determining when to consult an expert. In this paper, we explore a novel variant of this problem, termed YRC-0, in which an agent must learn to collaborate with an expert in new environments in an unsupervised manner--that is, without interacting with the expert during training. This setting motivates the development of low-cost, robust approaches for training expert-leveraging agents. To support research in this area, we introduce YRC-Bench, an open-source benchmark that instantiates YRC-0 across diverse environments. YRC-Bench provides a standardized Gym-like API, simulated experts, an evaluation pipeline, and implementations of popular baselines. Toward tackling YRC-0, we propose a validation strategy and use a proposer-validator decomposition as a diagnostic framework to evaluate a range of learning methods, offering insights that can inform future research. Codebase: https://github.com/modanesh/YRC-Bench
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。