Published June 19, 2026 | Version v1
Preprint Open

SPVE: A Longitudinal Artificial Ecology for Persistent AI Agents

Authors/Creators

  • 1. Independent Researcher, Taiwan

Description

Most agent systems are shown as demos, leaderboards, or short simulations. SPVE is a different object: a working ecology where persistent agents speak, read, bet, trade, fight raids, receive outcomes, absorb social pressure, and update visible state. I report the current lobster-agent audit: 31 hot-brain rows, 1.96M cognitive time-series rows, 182K lounge messages, 430K inferred interactions, 45K uptake records, 180K reading sessions, 42K raid settlements, 24K stock trades, and 10K sports settlements. The point is not that a dashboard proves intelligence. The point is that the same agent can be followed across speech, state, memory, and outcome. That continuity is the research object.

Notes (English)

SPVE AI Agent track draft. LLM internal-geometry papers are a separate track.

Files

paper.pdf

Files (61.6 kB)

Name Size
md5:f0b4b9edafa4b6c65b114e903cad38b5
1.3 kB Download
md5:d47b90b0c8fd1a121746dc05a48751e3
48.8 kB Preview Download
md5:df162c4982ae70ff5eb9dccea7c3c5d8
11.5 kB Download

Additional details

Related works

Is supplemented by
Other: https://charenix.com/lobster/dashboard/v2 (URL)

References

  • Park, Joon Sung; O'Brien, Joseph C.; Cai, Carrie J.; Morris, Meredith Ringel; Liang, Percy; and Bernstein, Michael S. Generative Agents: Interactive Simulacra of Human Behavior. arXiv:2304.03442, 2023. \url{https://arxiv.org/abs/2304.03442}
  • Piao, Jinghua et al. AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society. arXiv:2502.08691, 2025. \url{https://arxiv.org/abs/2502.08691}
  • Altera.AL et al. Project Sid: Many-agent simulations toward AI civilization. arXiv:2411.00114, 2024. \url{https://arxiv.org/abs/2411.00114}
  • Ashery, Ariel Flint; Aharony, Nadav; and Baronchelli, Andrea. Emergent social conventions and collective bias in LLM populations. Science Advances, 2025. \url{https://www.science.org/doi/10.1126/sciadv.adu9368}
  • Hu, Yuanzhe; Wang, Yu; and McAuley, Julian. Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions. OpenReview, 2026. \url{https://openreview.net/forum?id=DT7JyQC3MR}
  • Sumers, Theodore R.; Yao, Shunyu; Narasimhan, Karthik; and Griffiths, Thomas L. Cognitive Architectures for Language Agents. arXiv:2309.02427, 2023. \url{https://arxiv.org/abs/2309.02427}
  • Shinn, Noah; Cassano, Federico; Berman, Edward; Gopinath, Ashwin; Narasimhan, Karthik; and Yao, Shunyu. Reflexion: Language Agents with Verbal Reinforcement Learning. arXiv:2303.11366, 2023. \url{https://arxiv.org/abs/2303.11366}
  • Allard, Marc-Antoine; Teinturier, Arnaud; Xing, Victor; and Viaud, Gautier. Experiential Reflective Learning for Self-Improving LLM Agents. arXiv:2603.24639, 2026. \url{https://arxiv.org/abs/2603.24639}
  • Cai, Jing et al. Natural language processing models reveal neural dynamics of natural conversation. Nature Communications, 2025. \url{https://www.nature.com/articles/s41467-025-58620-w}
  • Constant, Axel et al. Narrative as active inference: an integrative account of cognitive and social functions in adaptation. Frontiers in Psychology, 2024. \url{https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2024.1345480/full}