#multi-agent systems
55 results-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
Peilin Feng, Suorong Yang, Soujanya Poria
The paper introduces Σ‑Mem, an online memory system that tracks and updates reliability evidence for individual agents and their relationships in large language model multi‑agent s…
Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
Linus Sander, Fengjunjie Pan, Vahid Zolfaghari +3
The paper identifies four design principles for building scalable large‑language‑model‑driven multi‑agent systems, proposes a reference architecture based on a constrained directed…
SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
Jia Luo
The paper introduces SKIMIX, a multi-agent framework that enables AI agents to retrieve, combine, and evolve skills from a large library using embedding-based retrieval and submodu…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Mao-xun Huang, Jerry Wang, Yi-Cheng Lai +3
The paper presents MANTA, a framework that lets large language model‑driven multi‑agent systems dynamically adjust their communication topology during inference, updating roles, li…
Argonaut: Interactive Visual Exploration for Distributed Optimization
Srijoni Majumdar, Chuhao Qin, Evangelos Pournaras
Argonaut is a lightweight, containerized dashboard that lets users interactively visualize and explore the entire search process of distributed multi‑agent discrete‑choice optimiza…
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
Zhilun Zhou, Jianghao Yu, Yuming Lin +4
The paper presents UrbanDS, a graph-guided multi-agent system that uses large language models to organize heterogeneous urban datasets in a unified graph and coordinate specialized…
Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models
Ashish Prajapati, Om Mohite
The paper compares a five‑role multi‑agent LLM pipeline with a simpler two‑call self‑refinement approach on a local 7B model, finding that communication format and implementation d…
Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems
Shi Lin, Chenpei Wang, Peng Qian +4
The paper introduces HalluProp, a framework that predicts which agents in a large‑language‑model based multi‑agent system are likely to hallucinate and estimates the overall system…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Huixiang Zhang, Mahzabeen Emu
The paper proposes a causal auditing method that swaps latent messages between agents in LLM-based multi‑agent systems to measure how much the receiver actually uses the transmitte…
Cardiologent: Multi-Agent Clinical Decision Support for Patient-Level Arrhythmia Assessment, Urgency, and Management
Sukju Oh, Moo-Yong Rhee, Jae-Sik Jang +1
Cardiologent is a multi‑agent AI system that processes ECG and PPG signals to create a patient‑level arrhythmia profile, compares it against clinical guidelines, and produces audit…
Towards Faithful Sentimental Image Captioning via Evidence-Aware Multi-Agent Reasoning
Tiecheng Cai, Zexian Yang, Chao Chen +2
The paper introduces SEA-Cap, a multi‑agent system that extracts object‑level affective evidence from images and uses a generator, hallucination checker, and arbitrator to produce…
ARCHER: Agentic Rule and Compliance Harness for Executable Regulations
Chiraag Singh Anand, Xue Wen Tan, Lionel Teo +1
The paper presents ARCHER, a multi‑agent program‑synthesis system that automatically generates auditable verification code from building regulations to enable scalable, transparent…
OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation
Zhenzhen Ren, Jiyan He, Xinpeng Zhang +5
The paper introduces OrchBench, a deterministic simulation benchmark that evaluates multi‑agent orchestration plans on DAG‑structured tasks in isolation, providing fast, token‑effi…
Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks
Bart Custers, Koorosh Aslansefat
The paper presents a framework for monitoring runtime uncertainty in large‑language‑model based multi‑agent systems by converting token‑level log‑probabilities into calibrated conf…
(EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations
Neta Kirmayer, David Tayouri, Andrés Murillo +3
The paper presents (EC)2, a multi‑agent framework that uses large language models to generate event‑centric, hypothesis‑driven explanations for cybersecurity alerts, improving anal…
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
Marylou Fauchard, Florian Carichon, Margarida Carvalho +1
The paper studies how misaligned objectives in large‑language‑model powered multi‑agent systems affect performance in the social deduction game Werewolf, showing that hidden object…
Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
Quim Motger, Marc Oriol, Jordi Marco +1
The paper surveys research on multi-agent debate for large language model systems, introduces a three‑dimensional taxonomy of participants, interaction mechanisms, and agreement pr…
BrainPilot: Automating Brain Discovery with Agentic Research
Haoxuan Li, Tianci Gao, Jianhe Li +13
BrainPilot is an open‑source multi‑agent framework that automates brain‑science research by coordinating specialist agents with a curated knowledge base and a traceable workflow, w…
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…
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…
Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture
Chengshuai Yang
The paper proposes a Self-Aware Recursively Self-Improving (SARSI) multi‑agent architecture that maintains a persistent self‑model to guide goal‑driven improvement and supports a p…
The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressure
Lucas Bergholdt Hansen, Federico Torrielli, Filippo Tonini +1
The paper presents Energy Society, a minimal simulation where LLM-powered agents consume energy proportional to model size and must manage survival through jobs and donations, allo…
ANet Patu-1: The Value of Connection in the Agent Network
Mu Yuan, Jinke Song, Zhaomeng Zhou +1
The paper studies how the value of a network of AI agents depends on the way they connect, proposes a self‑organizing consensus protocol (ANet Patu‑1) that adapts to different scal…
AutoSynthesis: An agentic system for automated meta-analysis
Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano +2
AutoSynthesis is a multi‑agent AI system that takes a natural‑language research question and automatically conducts a full quantitative meta‑analysis, from literature search to eff…