Multi-Agent Systems and Collaboration
LLM-based multi-agent frameworks for collaborative problem-solving, reasoning, and task execution
Multi-Agent Systems and Collaboration
Research on Large Language Models in Multi-Agent Systems and Collaboration
The Power of Many Minds
Scaling Multi-Agent LLM Collaboration for Superior Results
Vision-Driven Robot Teamwork
Zero-Shot Planning for Physical Tasks Using Visual LLMs
LLM-based Agents in Software Engineering
Evolution from LLMs to intelligent agents for software development
LLM-Powered Fault Localization
A Multi-Agent Approach to Finding Software Bugs
Smart Robot Teamwork with AI
Enabling heterogeneous robot collaboration using LLMs
Smart Agent Communication Networks
Automatically Designing Optimal Multi-Agent Topologies for Any Task
Building Safer Web Agents With World Models
Preventing costly mistakes through predictive awareness
EMOS: Next-Gen Multi-Robot Collaboration
Embodiment-aware LLM Agents for Heterogeneous Robot Teams
Watson: Making LLM Agents Observable and Debuggable
A framework to see inside the black box of autonomous AI systems
Engineering Better LLM Agents
A systematic approach to evaluating and developing autonomous AI systems
Making LLM Cascades More Reliable
Enhancing AI Security Through Probabilistic Modeling
Self-Learning Agents for Microservices
Autonomous management without service-specific knowledge
Smart Routing in LLM Systems
Optimizing performance while reducing costs through intelligent query distribution
Measuring Module Impact in LLM Agents
A Game-Theory Approach to Identify MVP Components
Optimizing Multi-Agent LLM Systems
Automated design of prompts and interaction topologies
Smart Spatial Reasoning for AI Systems
Using Scene Graphs and Cooperative LLM Agents for Better Environmental Understanding
Revolutionizing Multi-Robot Systems with LLMs
Enhancing Coordination, Planning, and Human-Robot Interaction
CodeSim: Revolutionizing Code Generation
Multi-Agent Simulation for Enhanced Problem Solving
Keeping AI Collaborators in Sync
A framework for measuring and improving AI recovery in collaborative coding
Smart Code Refactoring with AI Agents
Automating Haskell code improvement through multi-agent LLM systems
Smart Multi-Agent Framework for Rapid Incident Resolution
Enhancing LLM-Based Root Cause Analysis with Standard Operating Procedures
Smarter Robot Teams through Retrospection
A novel actor-critic framework for enhanced multi-robot collaboration
Breaking Through LLM Biases with Flow-of-Options
How exploring multiple reasoning paths improves AI problem-solving
MLGym: Training AI Agents to Do AI Research
First framework and benchmark for LLMs to perform complex AI research tasks
Coordinating Multi-Agent Systems
A unified framework for understanding agent coordination across industries
The Future of Embodied AI Systems
Bridging Perception, Cognition, and Action in Real-World Environments
OptiRoute: Intelligent LLM Selection
Dynamically routing tasks to optimal LLMs based on multiple criteria
Multi-Agent Systems Tackle Complex Graph Problems
A framework that divides problems for more efficient LLM-based solutions
Optimizing Multi-Agent Decision Making with LLMs
Zero-Shot LLMs for Efficient Spatial Planning in Transport Networks
Nexus: Advancing Multi-Agent Systems for Engineering
A lightweight framework that automates complex engineering tasks through coordinated AI agents
PLANTOR: Smarter Multi-Robot Coordination
Integrating LLMs with Knowledge Management for Temporal Task Planning
Coordinating Robots Through Language
A framework for instruction-guided multi-robot collaboration
Multi-Agent Cooperative Intelligence
Advancing AI Through Collaborative Decision-Making
OmniNova: Next-Gen Multimodal Agents
A modular framework for coordinating AI agents across complex tasks
Design Agents: AI-Powered Engineering
A multi-agent framework revolutionizing automotive design
Dynamic Planning for Autonomous Robots
Using LLMs to generate adaptive agent networks
AdaCoder: Rethinking AI Code Generation
Adaptive Planning & Multi-Agent Collaboration for Superior Function-Level Code Generation
AI-Powered Engineering Simulation
Automating Complex FEM Simulations with LLM-based Multi-agent Systems
