Simulations show update mechanisms decide coexistence versus dominance of upstream and downstream reciprocators, with a robust optimal network degree maximizing upstream reciprocity across conditions.
Nowak, and Jorge M
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Institutional delays trigger instability in multi-agent systems through delayed repression, with simulations identifying reactivity to lagged signals as the destabilizing factor rather than learning.
Using Moran-Fermi evolutionary dynamics, the paper derives conditions on community sentiment priors for audited-agent adoption and fixation bounds, while showing that self-audited agents are not generally sufficient to prevent harm.
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
citing papers explorer
-
Upstream reciprocity versus downstream reciprocity: Catalyzing cooperation
Simulations show update mechanisms decide coexistence versus dominance of upstream and downstream reciprocators, with a robust optimal network degree maximizing upstream reciprocity across conditions.
-
Delayed Repression and Emergent Instability in Adaptive Multi-Agent Systems
Institutional delays trigger instability in multi-agent systems through delayed repression, with simulations identifying reactivity to lagged signals as the destabilizing factor rather than learning.
-
The Two Genie Game: Adoption and Welfare in Audit-Grounded AI Governance
Using Moran-Fermi evolutionary dynamics, the paper derives conditions on community sentiment priors for audited-agent adoption and fixation bounds, while showing that self-audited agents are not generally sufficient to prevent harm.
-
Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.