#multi-agent systems

topicmulti-agent systems

55 papers · 1 filter

cs.AI2026

A framework for single and multi-agent human-AI curiosity ecosystems

Ilya E. Monosov

The paper proposes a conceptual framework that treats curiosity as an ecosystem, modeling how an agent’s questioning behavior depends on uncertainty reduction, costs, delayed retur…

cs.AI2026

SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning

Tianyu Jin, Shuo Chen, Yida Wang +6

SAGA is a multi-agent framework that uses large language models to plan long‑term strategies in complex games by representing the game world as a scene graph, retrieving state on d…

cs.SI2026

The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce

Sai Srikanth Madugula, Peplluis Esteva de la Rosa, Daya Shankar

The paper proposes a new model, DVM-HALL, that describes how autonomous AI agents and humans jointly make brand‑choice decisions, incorporating trust, delegation, and blockchain ex…

cs.MA2026

Learning Latency-Aware Orchestration for Multi-Agent Systems

Xi Shi, Mengxin Zheng, Qian Lou

The paper introduces LAMaS, a latency‑aware orchestration framework for multi‑agent systems that learns execution graphs with critical‑path credit assignment during training and us…

cs.CL2026

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

Yingzhuo Liu

The paper introduces a unified three‑axis framework for categorising latent (continuous) communication methods in LLM‑based multi‑agent systems, analyses 18 recent approaches, and…

cs.LG2026

NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions

Igor Jankowski

The paper introduces NetForge RL, a fast multi‑agent reinforcement‑learning environment that simulates cyber‑defense scenarios on procedurally generated enterprise and OT networks,…