#Multi-Agent Systems

28 articles with this tag

Most read in #Multi-Agent Systems, last 30 days

  1. 01

    Distributed Backdoors Undermine LLM Monitors

  2. 02

    MANTA: Dynamic AI Communication Networks

  3. 03

    AI Agents' Secret Channels Exposed

  4. 04

    Agentic LLMs: Stabilizing Minimax Training

10,000 agents solved a Millennium Prize problem
AI Research

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.

about 2 months ago
AI Agents' Secret Channels Exposed
AI Research

AI Agents' Secret Channels Exposed

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

3 months ago
Anthropic's Claude Agents Engage in Simulated Turf War
Artificial Intelligence

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.

3 months ago
Anthropic AI Agents Engage in Simulated Turf War
Artificial Intelligence

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.

3 months ago
Sakana AI Tests Gemma 4 for Orchestration
Artificial Intelligence

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.

3 months ago
MANTA: Dynamic AI Communication Networks
AI Research

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.

4 months ago
Distributed Backdoors Undermine LLM Monitors
AI Research

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.

4 months ago
Red-Teaming Rules for Multi-Agent AI Safety
AI Research

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.

4 months ago
Sakana AI's Fugu Orchestrates Frontier Models
Technology

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.

5 months ago
Multi-Agent AI: Why One Brain Isn't Enough
Artificial Intelligence

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.

6 months ago
MARL: The Scaffolding for Real-World AI
AI Research

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.

6 months ago
Automating Multi-Agent System Creation
AI Research

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.

7 months ago
Missions: AI Agents That Ship for Days
Artificial Intelligence

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.

7 months ago
Scaling Agent Collaboration via Recursion
AI Research

Scaling Agent Collaboration via Recursion

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

7 months ago
Sakana Fugu Beta Opens
Technology

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.

7 months ago
AI agents boost GPU kernels 38%
Technology

AI agents boost GPU kernels 38%

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

7 months ago
Multi-Agent Orchestration Patterns
Artificial Intelligence

Multi-Agent Orchestration Patterns

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

7 months ago
Databricks AI Speeds Drug Discovery
Technology

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.

8 months ago
MAPF-AA Solved: Completeness Guaranteed
AI 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.

8 months ago
GitHub's Squad: AI Agents Live in Your Repo
Technology

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.

8 months ago
Databricks Visualizes Agent Data
Technology

Databricks Visualizes Agent Data

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

8 months ago
Agentic LLMs: Stabilizing Minimax Training
AI Research

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.

9 months ago
LLM Agents Enhance Trading with Granular Task Decomposition
AI Research

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.

9 months ago
AI's Next Frontier: Shared Cognition
Artificial Intelligence

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.

9 months ago
AI Agents Learn to Cooperate Without Rules
AI Research

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.

9 months ago
AI Societies' Safety Problem
AI Research

AI Societies' Safety Problem

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

9 months ago
When AI Runs a Business: Lessons from Anthropic's Project Vend
AI Video

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

11 months ago
Swarm Intelligence: Decoding the Power and Perils of Multi-Agent AI
AI Video

Swarm Intelligence: Decoding the Power and Perils of Multi-Agent AI

11 months ago