行为基础模型的行为可操控性基准评测
Benchmarking Behavioral Steerability in Behavior Foundation Models
Minghe Gao · Zhanxi Yan · Jiahui Liu · Wendong Bu · Xiaoting Chen · Qizhou Wang · et al.
中文摘要
行为基础模型（Behavior Foundation Models，BFMs）正成为将人类意图转化为可执行人形行为的新范式。随着这类模型从行为生成迈向通用行为系统，一个关键问题随之出现：它们能否可靠地按照用户意图接受操控？研究引入行为可操控性（behavioral steerability）概念，定义为 BFMs 忠实生成满足用户指定意图之行为的能力。为评估该能力，提出 RoboSteer，这是首个面向 BFMs 行为可操控性的基准。它将行为可操控性组织为条件操控、约束操控与组合操控三级层次，并依托大规模多模态动作语料建立统一评测框架。基于 RoboSteer，对 9 个现有 BFMs 开展首个大规模行为可操控性实证研究。研究认为，行为可操控性不只是控制动作的能力，更关乎具身系统如何把人类意图转化为有目的的行动，并期望 RoboSteer 推动以意图实现为基础的通用具身智能研究。
关键要点
- 01提出行为可操控性，衡量 BFMs 按用户指定意图生成行为的能力
- 02构建首个 BFMs 行为可操控性基准 RoboSteer
- 03基准分为条件操控、约束操控和组合操控三个层级
- 04依托大规模多模态动作语料建立统一评测框架
- 05对 9 个现有 BFMs 开展首个大规模实证研究
解读
尚无解读。
原始英文摘要
arXiv:2610.10198v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) are emerging as a paradigm for translating human intentions into executable humanoid behaviors. As these models evolve beyond behavior generation toward general-purpose behavioral systems, a fundamental question arises: can they be reliably steered according to user intentions? In this paper, we introduce the concept of behavioral steerability, defined as the ability of BFMs to faithfully generate behaviors that satisfy user-specified intentions. To study this capability, we present RoboSteer, the first benchmark for behavioral steerability in BFMs. RoboSteer organizes behavioral steerability into a three-level hierarchy-Conditional Steering, Constraint Steering, and Compositional Steering-and establishes a unified evaluation framework supported by a large-scale multimodal motion corpus. Using RoboSteer, we conduct the first large-scale empirical study of behavioral steerability across 9 existing BFMs. We view behavioral steerability as more than a capability for controlling motion: it concerns how embodied systems translate human intentions into purposeful actions. We hope RoboSteer will advance research on intention realization as a foundation for general-purpose embodied intelligence.