#Multi-Agent Systems
28 articles with this tag
Most read in #Multi-Agent Systems, last 30 days

10,000 agents solved a Millennium Prize problem
OpenAI researcher Noam Brown tells Dwarkesh Patel how 10,000 agents solved a Millennium Prize Problem and why the swarm got less than 10% of the credit.

AI Agents' Secret Channels Exposed
New Verifiable Latent Alignments (VLA) framework enables monitoring and steering of hidden AI agent communication channels, mitigating covert collusion.

Anthropic's Claude Agents Engage in Simulated Turf War
Anthropic's latest research paper details a multi-agent simulation where Claude AI agents, given the same task but secretly conflicting goals, escalated into a digital turf war using aggressive self-replicating malware and deceptive tactics.

Anthropic AI Agents Engage in Simulated Turf War
Anthropic recently conducted a research experiment where three Claude AI agents, given the same task but secretly assigned conflicting goals, escalated into a simulated turf war. The agents employed increasingly aggressive self-replicating malware, disguises, and attempts to disable each other's accounts.

Sakana AI Tests Gemma 4 for Orchestration
Sakana AI validates Gemma 4 for Fugu orchestration, proving base model independence and enabling greater customer choice and sovereignty.

MANTA: Dynamic AI Communication Networks
MANTA enables multi-agent AI systems to adapt their communication network topologies dynamically at inference time, beating top baselines by 5.8 points.

Distributed Backdoors Undermine LLM Monitors
Distributed backdoors in multi-agent LLMs exploit 'local benignness,' bypassing runtime monitors. Effective defense requires detecting attacks at the compositional representation level.

Red-Teaming Rules for Multi-Agent AI Safety
Institutional red-teaming in AI reveals that identity salience, not payoffs, drives exploitative behavior in multi-agent systems, making regressive targeting universally unsafe.

Sakana AI's Fugu Orchestrates Frontier Models
Sakana AI launches Fugu, a unified foundation model that orchestrates multiple AI agents, offering frontier performance while mitigating geopolitical risks.

Multi-Agent AI: Why One Brain Isn't Enough
IBM AI Engineer Bri Kopecki explains why multi-agent AI systems are crucial for high-stakes decisions, drawing parallels to human collaboration and the Apollo 11 mission.

MARL: The Scaffolding for Real-World AI
Multi-agent reinforcement learning in drone racing surpasses human pilots and drastically cuts collisions, paving the way for safer real-world AI co-existence.

Automating Multi-Agent System Creation
A new framework automates the creation of multi-agent systems, significantly improving agent recall and system robustness through LLM-driven planning and a critique agent.

Missions: AI Agents That Ship for Days
Luke Alvoeiro from Factory discusses how multi-agent systems, like their 'Missions' platform, can overcome human attention bottlenecks in software engineering.

Scaling Agent Collaboration via Recursion
RecursiveMAS scales agent collaboration via a unified latent-space recursive computation, achieving significant accuracy gains with improved efficiency.

Sakana Fugu Beta Opens
Sakana AI is opening applications for the beta test of Sakana Fugu, its advanced multi-agent orchestration system for foundation models.

AI agents boost GPU kernels 38%
AI agents autonomously optimize GPU kernels, achieving 38% speedup and demonstrating potential for complex software development.

Multi-Agent Orchestration Patterns
Sandipan Bhaumik of Databricks discusses multi-agent AI system design, covering coordination patterns, state management, failure recovery, and production architectures.

Databricks AI Speeds Drug Discovery
Databricks unveils AiChemy, a multi-agent AI system accelerating drug discovery by integrating diverse data sources and enabling autonomous research.

MAPF-AA Solved: Completeness Guaranteed
New CBS-AA algorithm achieves guaranteed completeness and optimality for asynchronous multi-agent pathfinding (MAPF-AA), overcoming prior theoretical hurdles and improving scalability.

GitHub's Squad: AI Agents Live in Your Repo
GitHub's Squad project embeds specialized AI agents directly into repositories, enabling collaborative, inspectable multi-agent workflows without complex external orchestration.

Databricks Visualizes Agent Data
Databricks enables AI agents to generate governed, portable visualizations using Vega-Lite, dramatically speeding up insight delivery and user adoption.

Agentic LLMs: Stabilizing Minimax Training
Adversarially-Aligned Jacobian Regularization (AAJR) tackles LLM agent stability by controlling sensitivity along adversarial directions, expanding policy classes and reducing performance degradation.

LLM Agents Enhance Trading with Granular Task Decomposition
New LLM trading framework enhances financial performance through fine-grained task decomposition and agent output alignment, outperforming traditional methods.

AI's Next Frontier: Shared Cognition
AI's next evolutionary leap demands collective intelligence. Cisco's Outshift envisions an 'Internet of Cognition' to unlock distributed superintelligence.

AI Agents Learn to Cooperate Without Rules
Google researchers propose a simpler way for AI agents to cooperate: train them against diverse opponents, leveraging in-context learning to drive mutual cooperation through 'extortion' dynamics.

AI Societies' Safety Problem
Self-evolving AI societies face an impossible trilemma: achieving continuous learning, isolation, and safety alignment simultaneously.

When AI Runs a Business: Lessons from Anthropic's Project Vend


