EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid LLM-Genetic Programming: Supervising and Generating Diverse Behavior Trees for Autonomous Robot Evolution

Chi Jie Tan, Eiji Hayashi, Abbe Mowshowitz, Way Soong Lim

Robotics · 11.05.2026 · 15 (5) · 98

DOI: 10.3390/robotics15050098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics, online erschienen am 11.05.2026. Verfasst von Chi Jie Tan und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Genetic Programming (GP) for evolving Behavior Trees (BTs) in autonomous robots often suffer from premature convergence, even when adaptive mutation mechanisms are employed. This paper proposes a novel hybrid framework that integrates Large Language Model (LLM) supervision into GP, in which the LLM performs holistic population analysis, adaptively regulates mutation rates, and generates targeted BTs to proactively address behavioral gaps in the evolving population. Unlike conventional evolutionary operators, the LLM introduces high-level semantic guidance by seeding underrepresented behavioral archetypes, thereby complementing stochastic genetic variation with structured exploration. The proposed method is evaluated in a Unity-based multi-task robotic simulation environment. Experimental results show that the hybrid approach significantly outperforms baseline GP with standard adaptive mutation, achieving a 71.7% faster emergence of Complete Robots, a 65.2% faster emergence of Excellent Robots, and a 28% increase in behavioral diversity. Notably, the two systems exhibit opposite mutation dynamics: the LLM-guided system progressively reduces mutation rates to promote exploitation, whereas the baseline maintains a high mutation rate. In addition, the LLM generates approximately 40 targeted BTs per run, proactively seeding the population with underrepresented behavioral archetypes. These performance gains are obtained with only a 13% computational overhead.

Zitieren

APA

Tan, C. J., Hayashi, E., Mowshowitz, A., & Lim, W. S. (2026). Hybrid LLM-Genetic Programming: Supervising and Generating Diverse Behavior Trees for Autonomous Robot Evolution. Robotics, 15(5), 98. https://doi.org/10.3390/robotics15050098

Vancouver

Tan CJ, Hayashi E, Mowshowitz A, Lim WS. Hybrid LLM-Genetic Programming: Supervising and Generating Diverse Behavior Trees for Autonomous Robot Evolution. Robotics. 2026;15(5):98. doi:10.3390/robotics15050098

BibTeX
@article{Tan2026,
  author = {Tan, Chi Jie and Hayashi, Eiji and Mowshowitz, Abbe and Lim, Way Soong},
  title = {Hybrid LLM-Genetic Programming: Supervising and Generating Diverse Behavior Trees for Autonomous Robot Evolution},
  journal = {Robotics},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {98},
  doi = {10.3390/robotics15050098}
}
Kostenlos starten →