5 papers
Emergence of Reputation-Based Cooperation in LLM Agents
Kazuya Horibe, Kenji Itao, Wataru Toyokawa
Can cooperation among large language model (LLM) agents be evolutionarily stable against free-rider invasion? We study an indirect reciprocity donation game where LLM agents observ…
Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance
Kazuya Horibe, Masaomi Hatakeyama, Gen Masumoto +2
We study group decision-making in artificial societies where the rules of play are themselves subject to collective amendment. Using the self-amending game Nomic, we compare multip…
Agency at the Interface: Distinguishing Teleological from Structural Self-Organization via Internal Coarse-Graining and Downward Causation
Kazuya Horibe, Keisuke Suzuki
Agency is widely characterized as the capacity of a system to regulate its internal states toward self-generated goals, yet characterizing the functional basis of this autonomy req…
Evolvable Chemotons: Toward the Integration of Autonomy and Evolution
Kazuya Horibe, Daichi G. Suzuki
In this study, we provide a relatively simple simulation framework for constructing artificial life (ALife) with both autonomous and evolutionary aspects by extending chemoton mode…
Emergence of Implicit World Models from Mortal Agents
Kazuya Horibe, Naoto Yoshida
We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the o…