Jevolution：研究 AI 智能体通信与群体动态的框架

View PDF HTML (experimental)

Abstract:Experiments with remote decision-making agents depend on more than the policy: the world may change during inference, the simulator determines which actions are available, and births and immigration alter who can act. We present Jevolution, an instrumented spatial predator-prey framework that makes these dependencies explicit. Its reference implementation separates the evolving world, asynchronous request scheduling, controller adapters, and experiment records. The model combines local observations, energy and resource constraints, predefined signals, and inherited scalar traits. We describe these mechanisms using the ODD protocol and distinguish implemented controls from research questions requiring additional interventions. Free synthetic fixtures exercise scheduling, signaling, and inheritance against the pinned implementation; they validate specified software behavior rather than model intelligence or ecological realism. A completed communication case study illustrates the end-to-end workflow using Jev to control both species. Across 6 complete habitat-seed pairs, the mean signals-on minus signals-off difference in normalized rabbit abundance was -0.0095 (nominal 95% pair-bootstrap interval [-0.0772, 0.0602]). This small study does not resolve the direction of the signal-system effect. The contribution is an inspectable experimental system and its evidence boundaries, not a new policy-learning algorithm or a demonstration of emergent language, adaptive selection, or biological predictive validity.

Comments:	29 pages, 5 figures, 12 tables. Project website: this https URL
Subjects:	Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2610.14449 [cs.MA]
	(or arXiv:2610.14449v1 [cs.MA] for this version)
	https://doi.org/10.48550/arXiv.2610.14449 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xirui Huang [view email]
[v1] Sat, 10 Oct 2026 01:26:29 UTC (623 KB)