mlsanityData to 14 Oct 2026

Jevolution: A Framework for Studying Communication and Collective Dynamics in AI Agents

arXiv 2610.14449 ↗First posted 10 Oct 2026cs.MA cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 10 Oct 2026.

Builds on

19 of 35 references.

References · 19

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  3. 2017Deep Reinforcement Learning that Matterscited by 754
  4. 2016Learning Multiagent Communication with Backpropagationcited by 366
  5. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  6. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  7. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  8. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  9. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  10. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
  11. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  12. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 71
7 more
  1. 2019On the Pitfalls of Measuring Emergent Communicationcited by 71
  2. 2020Reinforcement Learning with Random Delayscited by 59
  3. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 49
  4. 2019Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agentscited by 44
  5. 2019Real-Time Reinforcement Learningcited by 40
  6. 2024Affordable Generative Agentscited by 9
  7. 2025Evolutionary Policy Optimizationcited by 4

Built on by

Not cited yet.