Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912587673763840 |
|---|---|
| author | Patania, Sabrina Annese, Luca Lambiase, Anna Pellegrini, Anita Foulsham, Tom Ruggeri, Azzurra Rossi, Silvia Serino, Silvia Ognibene, Dimitri |
| author_facet | Patania, Sabrina Annese, Luca Lambiase, Anna Pellegrini, Anita Foulsham, Tom Ruggeri, Azzurra Rossi, Silvia Serino, Silvia Ognibene, Dimitri |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models Patania, Sabrina Annese, Luca Lambiase, Anna Pellegrini, Anita Foulsham, Tom Ruggeri, Azzurra Rossi, Silvia Serino, Silvia Ognibene, Dimitri Computation and Language Artificial Intelligence Human-Computer Interaction Robotics I.2; I.2.7; I.2.10; J.4 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. |
| title | Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction Robotics I.2; I.2.7; I.2.10; J.4 |
| url | https://arxiv.org/abs/2509.11868 |