[2603.00117] PEPA: a Persistently Autonomous Embodied Agent with Personalities

[2603.00117] PEPA: a Persistently Autonomous Embodied Agent with Personalities

arXiv - AI 4 min read

About this article

Abstract page for arXiv paper 2603.00117: PEPA: a Persistently Autonomous Embodied Agent with Personalities

Computer Science > Robotics arXiv:2603.00117 (cs) [Submitted on 21 Feb 2026] Title:PEPA: a Persistently Autonomous Embodied Agent with Personalities Authors:Kaige Liu, Yang Li, Lijun Zhu, Weinan Zhang View a PDF of the paper titled PEPA: a Persistently Autonomous Embodied Agent with Personalities, by Kaige Liu and 3 other authors View PDF HTML (experimental) Abstract:Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task specifications limits their capacity for long-term deployment in dynamic, unstructured environments where continuous human intervention is impractical. We propose that personality traits provide an intrinsic organizational principle for achieving persistent autonomy. Analogous to genotypic biases shaping biological behavioral tendencies, personalities enable agents to autonomously generate goals and sustain behavioral evolution without external supervision. To realize this, we develop PEPA, a three-layer cognitive architecture that operates through three interacting systems: Sys3 autonomously synthesizes personality-aligned goals and refines them via episodic memory and daily self-reflection; Sys2 performs deliberative reasoning to translate goals into executable action plans; Sys1 grounds the agent in sensorimotor interaction, executing actions and recording experiences. We va...

Originally published on March 03, 2026. Curated by AI News.

Related Articles

[2601.07855] RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution
Machine Learning

[2601.07855] RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution

Abstract page for arXiv paper 2601.07855: RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution

arXiv - AI · 3 min ·
[2502.00262] INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation
Llms

[2502.00262] INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation

Abstract page for arXiv paper 2502.00262: INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Ha...

arXiv - AI · 4 min ·
[2508.00500] ProbGuard: Probabilistic Runtime Monitoring for LLM Agent Safety
Llms

[2508.00500] ProbGuard: Probabilistic Runtime Monitoring for LLM Agent Safety

Abstract page for arXiv paper 2508.00500: ProbGuard: Probabilistic Runtime Monitoring for LLM Agent Safety

arXiv - AI · 4 min ·
[2603.26660] Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning
Robotics

[2603.26660] Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning

Abstract page for arXiv paper 2603.26660: Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning

arXiv - AI · 4 min ·
More in Robotics: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime