Related papers: Scaling Multi-Agent Systems with Prospect-State Propagation

Scaling Multi-Agent Systems with Prospect-State Propagation

URL: http://arxiv.org/abs/2609.08033v1
Date: Mon, 07 Sep 2026 22:30:12 GMT
Title: Scaling Multi-Agent Systems with Prospect-State Propagation
Abstract summary: We show a phenomenon in which agent heterogeneity gradually decreases during simulation.<n>Inspired by prospect theory, PspMAS decouples each agent's micro state into a compact Prospect State and an expressive Semantic State.<n>These two components work complementarily, providing a scalable LLM-based multi-agent simulation solution.
Score: 8.564207831867272
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop [0.0]
We create a simulation of a large language model society using a few hundred agents.<n>We map perception and memory to an effective theory and a predicted $N$-trend of the surrogate error.
arXiv Detail & Related papers (2026-07-19T08:44:38Z)
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution [25.26084224278813]
Role-Agent harnesses a single Large Language Model (LLM) to function concurrently as both the agent and the environment.<n>Role-Agent consistently improves performance, yielding an average gain of over 4% over strong baselines.
arXiv Detail & Related papers (2026-06-09T14:28:07Z)
Attributing Emergence in Million-Agent Systems [68.53670424791751]
Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.<n>Such studies require attributing macro emergence to individual agents.<n>We adapt Aumann--Shapley path-integral attribution to LLM-powered MAS at million-agent scale.
arXiv Detail & Related papers (2026-05-12T01:49:41Z)
Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
arXiv Detail & Related papers (2026-02-19T06:35:07Z)
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling [47.029742241618635]
Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation.<n>We propose PhysicsAgentABM, which shifts inference to behaviorally coherent agent clusters.<n> Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines.
arXiv Detail & Related papers (2026-02-05T18:59:01Z)
Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective [54.77404771454794]
We develop a flexible and robust world model for Multi-Agent Reinforcement Learning (MARL) using diffusion models.<n>Our method, Diffusion-Inspired Multi-Agent world model (DIMA), achieves state-of-the-art performance across multiple multi-agent control benchmarks.
arXiv Detail & Related papers (2025-05-27T09:11:38Z)
LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation [66.52371505566815]
Large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence.<n>We present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs.<n>In LMAgent, besides chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce.
arXiv Detail & Related papers (2024-12-12T12:47:09Z)
Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization [8.140037969280716]
In multi-agent systems with large number of agents, contribution of each agent to value of other agents is minimal. We provide a novel Multi-Agent Reinforcement Learning (MARL) mechanism that minimizes variance across values of agents in the same state. We show that our approach reduces the variance in revenues earned by taxi drivers, while still providing higher joint revenues than leading approaches.
arXiv Detail & Related papers (2022-12-27T06:59:00Z)
ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in Multi-Agent Simulations [110.72725220033983]
Epsilon-Robust Multi-Agent Simulation (ERMAS) is a framework for learning AI policies that are robust to such multiagent sim-to-real gaps. ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations. In particular, ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations.
arXiv Detail & Related papers (2021-06-10T04:32:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.