用大模型模拟人类视角发展，提升协作效率
Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models
- 结合推理与行动框架，让大模型生成符合发展阶段的内心叙事
- 高发展阶段的叙事能显著提升协作效率，早期阶段结果更不稳定
- 适合研究人机协作、认知发展建模的学者参考
语言与具身视角理解对人类协作至关重要，但现有计算模型很少同时处理二者。本文研究了PerspAct系统，该系统将ReAct范式与大语言模型（LLMs）结合，基于Selman理论模拟视角发展的阶段性特征。通过扩展的导演任务，评估GPT在任务前生成与发展阶段一致的内部叙事的能力，并分析其对协作表现的影响（定性：动作选择；定量：任务效率）。结果表明，GPT能在任务前可靠生成符合发展层级的叙事，但在交互中常向更高级阶段演变，说明语言交流有助于优化内部表征。较高发展层级普遍提升协作有效性，而早期阶段在复杂情境下表现更不一致。研究揭示了将具身视角与语言整合进大模型的潜力，强调在语言与具身任务中评估内部言语的重要性。
原文摘要 · Abstract (English)
Language and embodied perspective taking are essential for human collaboration, yet few computational models address both simultaneously. This work investigates the PerspAct system [1], which integrates the ReAct (Reason and Act) paradigm with Large Language Models (LLMs) to simulate developmental stages of perspective taking, grounded in Selman's theory [2]. Using an extended director task, we evaluate GPT's ability to generate internal narratives aligned with specified developmental stages, and assess how these influence collaborative performance both qualitatively (action selection) and quantitatively (task efficiency). Results show that GPT reliably produces developmentally-consistent narratives before task execution but often shifts towards more advanced stages during interaction, suggesting that language exchanges help refine internal representations. Higher developmental stages generally enhance collaborative effectiveness, while earlier stages yield more variable outcomes in complex contexts. These findings highlight the potential of integrating embodied perspective taking and language in LLMs to better model developmental dynamics and stress the importance of evaluating internal speech during combined linguistic and embodied tasks.
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。