EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Symbiotic Alignment via Collective Predictive Coding: A Theoretical Framework for Co-Creative Human–AI Ecosystems

Tadahiro Taniguchi, Yusuke Hayashi, Momoha Hirose, Mizuki Oka, Ken Suzuki, Olaf Witkowski, Audrey Tang

Artificial Life · 27.10.2026 · 32 (3) · 270-298

DOI: 10.1162/artl.a.475 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Life, online erschienen am 27.10.2026. Verfasst von Tadahiro Taniguchi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Life Institute Kyoto University Ritsumeikan University. Hauptthemen laut MEDLINE: Artificial Intelligence, Ecosystem, Symbiosis. Die Arbeit nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid integration of artificial intelligence (AI) into society has surfaced systemic risks, particularly deep polarization exacerbated by algorithms optimizing for individual engagement. The dominant alignment paradigm, reliant on unilateral control (e.g., RLHF), is ill-suited to address these emergent collective dynamics. This paper proposes a philosophical and computational shift toward symbiotic alignment (SA), moving beyond top-down constraints to a framework of mutual adaptation and co-evolution. We ground SA in collective predictive coding (CPC), reframing human–AI symbiosis as participation in a symbol emergence system (SES). Mathematically, we formalize this interaction as multi-agent reinforcement learning (MARL) augmented by a collective regularization term, driving agents to minimize collective free energy (CFE) while preserving individual autonomy. Crucially, this formulation reveals that social coherence does not require uniformity; within this framework, we computationally reinterpret “plurality” as a stable multimodal distribution of shared beliefs, where diverse worldviews coexist through mutual negotiation. We conclude by outlining the research agenda for realizing this vision: designing AI agents capable of co-creative learning and social mechanisms (“gardeners”) that foster trust, thereby steering our technological future toward a flourishing plurality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceEcosystemSymbiosisHumansReinforcement Machine LearningAlgorithms

Stichwörter der Autor:innen

AI alignmentactive inferencecollective predictive codingfree energy principlehuman–AI symbiosispluralitysymbiotic alignmentsymbol emergence systems

Autor:innen und Institutionen

  • Artificial Life Institute Kyoto University Ritsumeikan University.
  • Artificial Life Institute AI Alignment Network Humanity Brain hayashi@aialign.net.
  • Artificial Life Institute Kyoto University.
  • Artificial Life Institute Chiba Institute of Technology.
  • Artificial Life Institute The University of Tokyo.
  • Artificial Life Institute Cross Labs The University of Tokyo.

Zitieren

APA

Taniguchi, T., Hayashi, Y., Hirose, M., Oka, M., Suzuki, K., Witkowski, O., & Tang, A. (2026). Symbiotic Alignment via Collective Predictive Coding: A Theoretical Framework for Co-Creative Human–AI Ecosystems. Artificial Life, 32(3), 270-298. https://doi.org/10.1162/artl.a.475

Vancouver

Taniguchi T, Hayashi Y, Hirose M, Oka M, Suzuki K, Witkowski O, et al. Symbiotic Alignment via Collective Predictive Coding: A Theoretical Framework for Co-Creative Human–AI Ecosystems. Artificial Life. 2026;32(3):270-298. doi:10.1162/artl.a.475

BibTeX
@article{Taniguchi2026,
  author = {Taniguchi, Tadahiro and Hayashi, Yusuke and Hirose, Momoha and Oka, Mizuki and Suzuki, Ken and Witkowski, Olaf and Tang, Audrey},
  title = {Symbiotic Alignment via Collective Predictive Coding: A Theoretical Framework for Co-Creative Human–AI Ecosystems},
  journal = {Artificial Life},
  year = {2026},
  volume = {32},
  number = {3},
  pages = {270--298},
  doi = {10.1162/artl.a.475}
}
Kostenlos starten →