104 articles tagged with #multi-agent-systems. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce CHIEF, a new framework that improves failure analysis in LLM-powered multi-agent systems by transforming execution logs into hierarchical causal graphs. The system uses oracle-guided backtracking and counterfactual attribution to better identify root causes of failures, outperforming existing methods on benchmark tests.
Researchers introduce RUMAD, a reinforcement learning framework that optimizes multi-agent AI debate systems by dynamically controlling communication topology. The system achieves over 80% reduction in computational costs while improving reasoning accuracy across benchmark tests, with strong generalization capabilities across different task domains.
Researchers developed BUSD-Agent, an AI framework for breast cancer screening that uses cascaded agents and experience-guided decision-making to reduce unnecessary biopsies. The system achieved a 22% reduction in biopsy referrals while improving diagnostic accuracy through retrieval-based learning from past cases.
Researchers introduce CoMind, a multi-agent AI system that leverages community knowledge to automate machine learning engineering tasks. The system achieved a 36% medal rate on 75 past Kaggle competitions and outperformed 92.6% of human competitors in eight live competitions, establishing new state-of-the-art performance.
Researchers present AgentFail, a dataset of 307 real-world failure cases from agentic workflow platforms, analyzing how multi-agent AI systems fail and can be repaired. The study reveals that failures in these low-code orchestrated AI workflows propagate differently than traditional software, making them harder to diagnose and fix.
Researchers introduced IntentCUA, a multi-agent framework for computer automation that achieved 74.83% task success rate through intent-aligned planning and memory systems. The system uses coordinated agents (Planner, Plan-Optimizer, and Critic) to reduce error accumulation and improve efficiency in long-horizon desktop automation tasks.
Researchers have developed LumiMAS, a comprehensive framework for monitoring and detecting failures in multi-agent systems that incorporate large language models. The framework features three layers: monitoring and logging, anomaly detection, and anomaly explanation with root cause analysis, addressing the unique challenges of observing entire multi-agent systems rather than individual agents.
Researchers propose an agentic AI framework using multiple LLM-based agents to optimize cell-free Open RAN networks through intent-driven automation. The system reduces active radio units by 42% in energy-saving mode while cutting memory usage by 92% through parameter-efficient fine-tuning.
Researchers from Pennsylvania State University and Duke University have introduced automated failure attribution for multi-agent systems, a methodology that transforms the complex process of identifying system failures and their causes into a quantifiable and analyzable problem. This development could significantly improve the debugging and accountability processes in multi-agent AI system development.
Researchers have developed Unicorn, a universal reinforcement learning framework for adaptive traffic signal control that addresses challenges in heterogeneous urban traffic networks. The system uses collaborative multi-agent reinforcement learning with unified mapping and specialized representation modules to optimize traffic flow across diverse intersection topologies.
Researchers introduce MA-EgoQA, a benchmark for evaluating AI models' ability to understand multiple egocentric video streams from embodied agents simultaneously. The benchmark includes 1.7k questions across five categories and reveals current approaches struggle with multi-agent system-level understanding.
Researchers developed a multi-agent simulation framework using reinforcement learning to model archaeological mobility patterns in complex terrain. The system combines global path planning with local adaptation to simulate human and animal movement in historical landscapes, demonstrated through pursuit scenarios and transport analysis.
Researchers developed a multi-agent influence diagram framework to model hybrid cyber threats and evaluate countermeasures through simulated strategic interactions. The study analyzed 1000 semi-synthetic scenarios of cyber attacks on critical infrastructure to assess the effectiveness of five different counter-hybrid threat measures.
Researchers evaluated five Multimodal Large Language Models (MLLMs) on their ability to reason about social norms in both text and image scenarios. GPT-4o performed best overall, while all models showed superior performance with text-based norm reasoning compared to image-based scenarios.
Researchers have developed HAMLET, a hierarchical multi-agent AI framework that creates immersive, interactive theatrical experiences using large language models. The system generates narrative blueprints from simple topics and enables AI actors to perform with adaptive reasoning, emotional states, and physical interactions with scene props.
Researchers present new theoretical frameworks for fair allocation of indivisible goods when limited sharing is allowed among agents. The study introduces cost-sensitive sharing mechanisms and proves that maximin share (MMS) allocations can be guaranteed under specific conditions, while also establishing new fairness concepts like Sharing Maximin Share (SMMS).
Researchers developed a multi-agent platform using large language models to study affective polarization in social media through virtual communities. The framework addresses limitations of real-world studies by creating simulated environments where AI agents engage in discussions to analyze political and social divisions.
Researchers introduce ConEQsA, an AI framework that enables embodied agents to handle multiple questions simultaneously in 3D environments with urgency-aware scheduling. The system uses shared memory to reduce redundant exploration and includes a new benchmark with 200 questions across 40 indoor scenes.
Researchers have developed HVR-Met, a multi-agent AI system that uses a 'Hypothesis-Verification-Replanning' mechanism to diagnose extreme weather events through sophisticated iterative reasoning. The system addresses current limitations in AI weather forecasting by integrating expert knowledge and providing professional-grade diagnostic capabilities for complex meteorological scenarios.
Researchers developed a multi-agent AI framework for adaptive Augmented Reality robot training that uses Large Language Models to dynamically adjust learning environments based on individual cognitive profiles. The system processes multimodal inputs including voice, physiology, and robot data to personalize industrial robot training experiences in real-time.
Researchers introduced PaperRepro, a two-stage AI agent system that automates the assessment of computational reproducibility in social science research papers. The system achieved a 21.9% improvement over existing baselines on the REPRO-Bench benchmark by separating code execution from evaluation phases.
Researchers introduce SIGMAS, a self-supervised AI framework for identifying group structures in multi-agent swarms like drone fleets without ground-truth supervision. The system uses second-order interactions to infer latent group memberships from agent trajectories, demonstrating robust performance across diverse synthetic swarm scenarios.
ViviDoc is a new human-agent collaborative system that generates interactive educational documents using a multi-agent pipeline and Document Specification framework. The system allows educators to review and refine AI-generated content plans before code production, significantly outperforming naive AI generation methods.
A research position paper examines the integration of Large Language Models (LLMs) in agent-based social simulations, highlighting both opportunities and limitations. The study proposes Hybrid Constitutional Architectures that combine classical agent-based models with small language models and LLMs to balance expressive flexibility with analytical transparency.
Researchers have developed gossip algorithms that enable decentralized networks to reach consensus on rankings using Borda and Copeland methods without central coordination. The approach allows autonomous agents to compute global ranking consensus through local interactions, with applications in peer-to-peer networks, IoT, and multi-agent systems.
