Metraipolis › archive › dc_e2c2f90ad031
Scaling Multi-Agent Systems with Prospect-State Propagation — arXiv:2609.08033
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08033
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:23:53.761Z
- SHA-256 of the archived text
b1c9559bb1973e19f67d3636d3b81598c4ab81bd46281ec4c61e87635ca76cf1- Stable URL of this page
https://metraipolis.com/documento/dc_e2c2f90ad031
How to cite
Scaling Multi-Agent Systems with Prospect-State Propagation — arXiv:2609.08033 — arXiv (en), https://arxiv.org/abs/2609.08033 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2c2f90ad031 (Metraipolis archive dc_e2c2f90ad031, sha256 b1c9559bb1973e19f67d3636d3b81598c4ab81bd46281ec4c61e87635ca76cf1)
BibTeX
@misc{dce2c2f90ad031,
title = {Scaling Multi-Agent Systems with Prospect-State Propagation — arXiv:2609.08033},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08033},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2c2f90ad031; sha256 b1c9559bb1973e19f67d3636d3b81598c4ab81bd46281ec4c61e87635ca76cf1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08033. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents. However, naive scaling strategies face challenges. For example, in economic simulations, large-scale MAS typically discard semantically rich economic states, i.e., agent behavioral trajectories, which are key drivers of macroeconomic fluctuations. In this paper, we reveal a phenomenon in which agent heterogeneity gradually decreases during simulation, and propose Prospect-State Propagation for Multi-Agent Systems (PspMAS). Inspired by prospect theory, PspMAS decouples each agent's micro state into a compact Prospect State and an expressive Semantic State. The former records psychological traces through a lightweight, parallelizable propagator and continuously injects heterogeneity into the system. The latter leverages the strong perception, reasoning, planning, and decision-making abilities of LLMs. These two components work complementarily, providing a scalable LLM-based multi-agent simulation solution. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CY). Categorie arXiv: Multiagent Systems (cs.MA) ; Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.08033 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:05:53.957Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).