论文arXiv 2611.175496 天前
Talk to Act基准发布:验证270M-8B开源模型零样本机器人意图解析能力
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Talk to Act: A Synthetic Multi-Turn Dialogue Benchmark for Human Intent Extraction and Action Planning in Robotics(arXiv 2611.17549)
核心内容
针对现有人机交互系统依赖刚性指令且缺乏真实多轮对话数据的瓶颈,研究团队发布合成数据集Talk to Act。该基准覆盖多场景与用户画像,标注了动作意图、对象引用及任务计划,旨在解决自然语言理解中的歧义与上下文依赖问题,为评估机器人在复杂语境下的指令解析能力提供标准化测试环境。
技术路线将意图提取重构为工具调用问题,要求模型输出接地于对话的结构化函数调用。评测涵盖270M至8B参数的开源小模型,结果表明无需任务特定微调,紧凑模型即可实现合理的意图提取与动作规划性能。这验证了轻量级模型在本地部署场景下的基线可用性,后续结合微调与真实数据有望进一步提升实战表现。
关键看点
- 合成数据基准:构建包含动作意图、对象引用及任务计划的多轮对话数据集,弥补真实HRI数据在多义性与上下文依赖维度的缺失
- 工具调用范式:将自然语言意图提取转化为结构化函数调用生成任务,强制模型输出参数接地于对话内容的可执行动作指令
- 小模型零样本验证:270M至8B参数开源模型无需微调即具备意图解析与规划能力,确立紧凑型模型本地部署的性能基线
- 端侧部署潜力:证实未微调的小参数量模型已满足基础会话机器人需求,为低算力边缘端具身智能应用提供可行技术路径
工程与产业观察
该工作证明了270M-8B级开源模型在零样本下具备机器人指令解析基线能力,降低了端侧具身智能对大模型的依赖。将意图理解转化为工具调用的范式,为小模型在本地化、低延迟机器人交互系统中的工程落地提供了关键验证与数据支撑。
英文摘要 (Abstract)
Multi-turn conversational human-robot interaction (HRI) continues to be a challenging problem in robotics, as many existing systems rely on rigid, command-driven interfaces that can be unintuitive for users. Recent advances in Large Language Models (LLMs) provide a promising direction, given their ability to process natural language, generate structured outputs, and support tool-based reasoning, all of which are relevant for interpreting user intent in robotic settings. However, progress in this area is constrained by the limited availability of datasets and benchmarks that capture the nuances of real-world human communication, such as multi-turn dialogue, ambiguity, and context-dependent requests. In this work, we present a synthetically generated multi-turn dialogue dataset for HRI, annotated with action intents, object references, and task plans across a range of scenarios and user personas. Our primary focus is on evaluating the capability of small, open-weight language models for robotic tasks, particularly in settings where local deployment and efficiency are important. To this end, we frame intent extraction as a tool-calling problem where each predicted action corresponds to a structured function call with arguments grounded in the dialogue and benchmark models ranging from 270M to 8B parameters on their ability to perform intent extraction and action planning without task-specific fine-tuning. Our results show that these models can achieve reasonable performance on the task even at relatively small scales and without any task-specific fine-tuning. This suggests that compact, locally deployable models already provide a useful baseline for conversational robotic systems. We expect that task-specific fine-tuning and more realistic training data will enhance performance further and make such models increasingly suitable for real-world robotic applications.
作者:Deepu Krishnareddy, Mohammad Haziq Khan, Michael Danner, Matthias R"atsch
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)