Federated Reinforcement Learning Powers PALCAS: An Intelligent Lane Change Decision System for Autonomous Driving
A research team has proposed PALCAS, a Priority-Aware Intelligent Lane Change Advisory System based on multi-agent feder…
🏷️ Agent System
28 articles about 'Agent System'
New Study Reveals the 'Consensus Paradox' in AI Multi-Agent Swarms
A new study based on 36 experiments and 12,804 decision trajectories challenges the fundamental 'wisdom of the crowd' as…
Web2BigTable: Multi-Agent LLMs Enable Internet-Scale Information Search and Extraction
A research team has proposed the Web2BigTable system, featuring a bi-level multi-agent architecture that combines large …
New Study Optimizes Stop-Loss and Take-Profit Strategies for AI Trading Agent Swarms
A latest arXiv paper proposes a method for optimizing stop-loss and take-profit parameters for autonomous cryptocurrency…
TRUST Framework: A New Trust Paradigm for Decentralized AI Services
A latest arXiv paper proposes the TRUST framework, addressing four core pain points of large reasoning models and multi-…
Multi-Agent AI Enables Automatic Generation of ML Pipelines
A latest arXiv paper proposes a five-agent architecture that can automatically generate end-to-end machine learning pipe…
Microsoft Research: What Happens When AI Agents Interact at Scale
Microsoft Research publishes new findings revealing that individually safe AI agents don't guarantee the overall safety …
Multi-Agent Collaboration: The Hardest Engineering Challenge in Scaling AI
Intuit's engineering team shares practical experience with multiple AI agents working collaboratively in complex systems…
The Multi-Agent Resource Allocation Dilemma: Fewer and Stronger, or More and Simpler?
A new arXiv study introduces the 'Split over n' resource-sharing problem, exploring whether limited resources in multi-a…
SciHorizon-DataEVA: An AI Agent That Automatically Evaluates the AI-Readiness of Scientific Data
A latest arXiv paper introduces the SciHorizon-DataEVA system, which leverages an agentic architecture to automatically …
QuantClaw: Finding the Optimal Quantization Precision Balance for OpenClaw Agents
A research team releases QuantClaw, systematically analyzing the impact of quantization techniques on OpenClaw autonomou…
Superminds Test: Can Collective Intelligence Emerge from a Society of 2 Million AI Agents?
A research team conducted the first empirical evaluation of collective intelligence in a large-scale autonomous agent so…