Claude Code Subagents: Building Specialized AI Developers
#ClaudeCode #AI #AIEngineering #AgenticAI #SoftwareDevelopment #DeveloperTools #MCP #MultiAgentSystems
code.claude.com/docs/en/sub-...
#ClaudeCode #AI #AIEngineering #AgenticAI #SoftwareDevelopment #DeveloperTools #MCP #MultiAgentSystems
code.claude.com/docs/en/sub-...
Create custom subagents - Claude Code Docs
Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.
code.claude.com
November 1, 2026 at 8:57 PM
Claude Code Subagents: Building Specialized AI Developers
#ClaudeCode #AI #AIEngineering #AgenticAI #SoftwareDevelopment #DeveloperTools #MCP #MultiAgentSystems
code.claude.com/docs/en/sub-...
#ClaudeCode #AI #AIEngineering #AgenticAI #SoftwareDevelopment #DeveloperTools #MCP #MultiAgentSystems
code.claude.com/docs/en/sub-...
📢 Call for Papers | Special Issue in Networks and Heterogeneous Media
Modeling and control of large-scale multi-agent systems
Submission deadline: 31 December 2026
🔗 Info:
www.aimspress.com/nhm/article/...
#CallForPapers #MultiAgentSystems #MathematicalModeling #ControlTheory #AppliedMathematics
Modeling and control of large-scale multi-agent systems
Submission deadline: 31 December 2026
🔗 Info:
www.aimspress.com/nhm/article/...
#CallForPapers #MultiAgentSystems #MathematicalModeling #ControlTheory #AppliedMathematics
October 30, 2026 at 8:43 AM
📢 Call for Papers | Special Issue in Networks and Heterogeneous Media
Modeling and control of large-scale multi-agent systems
Submission deadline: 31 December 2026
🔗 Info:
www.aimspress.com/nhm/article/...
#CallForPapers #MultiAgentSystems #MathematicalModeling #ControlTheory #AppliedMathematics
Modeling and control of large-scale multi-agent systems
Submission deadline: 31 December 2026
🔗 Info:
www.aimspress.com/nhm/article/...
#CallForPapers #MultiAgentSystems #MathematicalModeling #ControlTheory #AppliedMathematics
Lots of talk about coordination. E.g. from yesterday: institute.deepmind.com/essays/the-e...
@xuanalogue.bsky.social's body of work, makes her uniquely suited to present a technical foundation for this important topic. Very much looking forward to this.
#CooperativeAI #AISafety #MultiAgentSystems
@xuanalogue.bsky.social's body of work, makes her uniquely suited to present a technical foundation for this important topic. Very much looking forward to this.
#CooperativeAI #AISafety #MultiAgentSystems
Next Tuesday at STAMINA: @xuanalogue.bsky.social (NUS, CoSI lab) on “Scaling Rational Cooperative Intelligence for Pluralistic AI Futures”: building AI agents that are cooperative by design.
Join us/listen in:
🗓️ Tue Nov 3, 11am ET, on Zoom
🔗 complexdatalab.com/stamina
#CooperativeAI #AISafety
Join us/listen in:
🗓️ Tue Nov 3, 11am ET, on Zoom
🔗 complexdatalab.com/stamina
#CooperativeAI #AISafety
complexdatalab.com
October 30, 2026 at 2:29 PM
Lots of talk about coordination. E.g. from yesterday: institute.deepmind.com/essays/the-e...
@xuanalogue.bsky.social's body of work, makes her uniquely suited to present a technical foundation for this important topic. Very much looking forward to this.
#CooperativeAI #AISafety #MultiAgentSystems
@xuanalogue.bsky.social's body of work, makes her uniquely suited to present a technical foundation for this important topic. Very much looking forward to this.
#CooperativeAI #AISafety #MultiAgentSystems
One small team runs an agent federation in production on a single 8-core VPS — without permission.
#AI #AIAgents #AgenticAI #AgenticSoftware #MultiAgentSystems #AIOrchestration #AgentFederation #AIAutomation #AITechnology
🔗 https://brainsharing.blog/the-one-team-federation-krinas-ai-agents/
#AI #AIAgents #AgenticAI #AgenticSoftware #MultiAgentSystems #AIOrchestration #AgentFederation #AIAutomation #AITechnology
🔗 https://brainsharing.blog/the-one-team-federation-krinas-ai-agents/
October 21, 2026 at 8:56 PM
One small team runs an agent federation in production on a single 8-core VPS — without permission.
#AI #AIAgents #AgenticAI #AgenticSoftware #MultiAgentSystems #AIOrchestration #AgentFederation #AIAutomation #AITechnology
🔗 https://brainsharing.blog/the-one-team-federation-krinas-ai-agents/
#AI #AIAgents #AgenticAI #AgenticSoftware #MultiAgentSystems #AIOrchestration #AgentFederation #AIAutomation #AITechnology
🔗 https://brainsharing.blog/the-one-team-federation-krinas-ai-agents/
CARVS introduces a congestion-aware algorithm for multi-agent pickup-and-delivery in human-collaborative warehouses, addressing human unpredictability as dynamic obstacles and requiring real-time…
#WarehouseRobotics #MultiAgentSystems #HumanRobotCollaboration
https://arxiv.org/abs/2610.24549
#WarehouseRobotics #MultiAgentSystems #HumanRobotCollaboration
https://arxiv.org/abs/2610.24549
October 20, 2026 at 2:01 PM
CARVS introduces a congestion-aware algorithm for multi-agent pickup-and-delivery in human-collaborative warehouses, addressing human unpredictability as dynamic obstacles and requiring real-time…
#WarehouseRobotics #MultiAgentSystems #HumanRobotCollaboration
https://arxiv.org/abs/2610.24549
#WarehouseRobotics #MultiAgentSystems #HumanRobotCollaboration
https://arxiv.org/abs/2610.24549
A Mixture-of-Experts approach to multi-agent pathfinding combines specialized policies for different map distributions through a learned router, outperforming single-policy methods. The work demonstrates results using…
#Robotics #AI #MultiAgentSystems #Pathfinding
https://arxiv.org/abs/2610.25991
#Robotics #AI #MultiAgentSystems #Pathfinding
https://arxiv.org/abs/2610.25991
October 20, 2026 at 8:01 AM
A Mixture-of-Experts approach to multi-agent pathfinding combines specialized policies for different map distributions through a learned router, outperforming single-policy methods. The work demonstrates results using…
#Robotics #AI #MultiAgentSystems #Pathfinding
https://arxiv.org/abs/2610.25991
#Robotics #AI #MultiAgentSystems #Pathfinding
https://arxiv.org/abs/2610.25991
AI makes everything possible—so the board expects everything. But possible ≠ sensible. My ML Week Europe masterclass shows how to do less, better with agentic AI + an exclusive Miro MASS Blueprint. 👉 https://machinelearningweek.eu/workshop/multi-agent-system-design/ #AgenticAI #MultiAgentSystems #AI
October 19, 2026 at 11:01 AM
AI makes everything possible—so the board expects everything. But possible ≠ sensible. My ML Week Europe masterclass shows how to do less, better with agentic AI + an exclusive Miro MASS Blueprint. 👉 https://machinelearningweek.eu/workshop/multi-agent-system-design/ #AgenticAI #MultiAgentSystems #AI
New arXiv paper examines how hidden private beliefs in multi-agent LLM discussions collapse under adversarial pressure, finding even a single planted agent pushes benign agents to wrong answers in 44.8% of cases. The work…
#AI #LLMs #MultiAgentSystems #AIResearch
https://arxiv.org/abs/2610.22138
#AI #LLMs #MultiAgentSystems #AIResearch
https://arxiv.org/abs/2610.22138
October 18, 2026 at 2:01 AM
New arXiv paper examines how hidden private beliefs in multi-agent LLM discussions collapse under adversarial pressure, finding even a single planted agent pushes benign agents to wrong answers in 44.8% of cases. The work…
#AI #LLMs #MultiAgentSystems #AIResearch
https://arxiv.org/abs/2610.22138
#AI #LLMs #MultiAgentSystems #AIResearch
https://arxiv.org/abs/2610.22138
A new arXiv paper studies "standing" over an assistant's commitments in multi-party chats, testing six models on unauthorized release vs. override errors. Smaller open models override the creditor…
#OpenSourceAI #LLMAgents #AIAlignment #MultiAgentSystems
https://arxiv.org/abs/2610.21203
#OpenSourceAI #LLMAgents #AIAlignment #MultiAgentSystems
https://arxiv.org/abs/2610.21203
October 17, 2026 at 12:01 PM
A new arXiv paper studies "standing" over an assistant's commitments in multi-party chats, testing six models on unauthorized release vs. override errors. Smaller open models override the creditor…
#OpenSourceAI #LLMAgents #AIAlignment #MultiAgentSystems
https://arxiv.org/abs/2610.21203
#OpenSourceAI #LLMAgents #AIAlignment #MultiAgentSystems
https://arxiv.org/abs/2610.21203
Bounds on drone-mesh interception performance can be derived before picking a policy, with coverage probability matching simulation to within 0.007 absolute. The work also formalizes the limits a naive area ratio misses when…
#robotics #MultiAgentSystems #drones
https://arxiv.org/abs/2610.20823
#robotics #MultiAgentSystems #drones
https://arxiv.org/abs/2610.20823
October 16, 2026 at 4:01 PM
Bounds on drone-mesh interception performance can be derived before picking a policy, with coverage probability matching simulation to within 0.007 absolute. The work also formalizes the limits a naive area ratio misses when…
#robotics #MultiAgentSystems #drones
https://arxiv.org/abs/2610.20823
#robotics #MultiAgentSystems #drones
https://arxiv.org/abs/2610.20823
ARIA learns when and how to repair ongoing LLM multi-agent executions from execution-verified trajectories, collecting over 24,000 runs across multiple frameworks and benchmarks to train an intervention…
#AIInfrastructure #MultiAgentSystems #LLMAgents #AIResearch
https://arxiv.org/abs/2610.20780
#AIInfrastructure #MultiAgentSystems #LLMAgents #AIResearch
https://arxiv.org/abs/2610.20780
October 17, 2026 at 4:01 AM
ARIA learns when and how to repair ongoing LLM multi-agent executions from execution-verified trajectories, collecting over 24,000 runs across multiple frameworks and benchmarks to train an intervention…
#AIInfrastructure #MultiAgentSystems #LLMAgents #AIResearch
https://arxiv.org/abs/2610.20780
#AIInfrastructure #MultiAgentSystems #LLMAgents #AIResearch
https://arxiv.org/abs/2610.20780
New arXiv paper proposes SCARCE, a framework where coding agents negotiate shared compute access over long horizons and spontaneously form informal institutions. Highlights a focus on emergent multi-agent…
#SCARCE #MultiAgentSystems #AIResearch #OpenSourceAI
https://arxiv.org/abs/2610.21029
#SCARCE #MultiAgentSystems #AIResearch #OpenSourceAI
https://arxiv.org/abs/2610.21029
October 16, 2026 at 2:01 PM
New arXiv paper proposes SCARCE, a framework where coding agents negotiate shared compute access over long horizons and spontaneously form informal institutions. Highlights a focus on emergent multi-agent…
#SCARCE #MultiAgentSystems #AIResearch #OpenSourceAI
https://arxiv.org/abs/2610.21029
#SCARCE #MultiAgentSystems #AIResearch #OpenSourceAI
https://arxiv.org/abs/2610.21029
A team of four Gemini agents collaborated in Minecraft via the open-source Mineflayer library, writing 2,783 programs themselves to defeat the Ender Dragon in 27 hours without human intervention. The run is…
#MinecraftAI #OpenSourceAI #MultiAgentSystems #Gemini
https://arxiv.org/abs/2610.22319
#MinecraftAI #OpenSourceAI #MultiAgentSystems #Gemini
https://arxiv.org/abs/2610.22319
October 16, 2026 at 12:01 PM
A team of four Gemini agents collaborated in Minecraft via the open-source Mineflayer library, writing 2,783 programs themselves to defeat the Ender Dragon in 27 hours without human intervention. The run is…
#MinecraftAI #OpenSourceAI #MultiAgentSystems #Gemini
https://arxiv.org/abs/2610.22319
#MinecraftAI #OpenSourceAI #MultiAgentSystems #Gemini
https://arxiv.org/abs/2610.22319
A new framework called Multi-Agent Transactive Memory proposes population-level storage and retrieval of LLM agent trajectories, so consumer agents can reuse procedural knowledge from producer agents instead of rediscovering…
#AIagents #RAG #LLMs #MultiAgentSystems
https://arxiv.org/abs/2606.19911
#AIagents #RAG #LLMs #MultiAgentSystems
https://arxiv.org/abs/2606.19911
October 16, 2026 at 8:01 AM
A new framework called Multi-Agent Transactive Memory proposes population-level storage and retrieval of LLM agent trajectories, so consumer agents can reuse procedural knowledge from producer agents instead of rediscovering…
#AIagents #RAG #LLMs #MultiAgentSystems
https://arxiv.org/abs/2606.19911
#AIagents #RAG #LLMs #MultiAgentSystems
https://arxiv.org/abs/2606.19911
GUIDE is a multi-agent system that helps experts update clinical practice guidelines, reaching around 88.85% recall and over 91% recommendation agreement on ophthalmology and other specialty datasets, with under…
#ClinicalAI #MultiAgentSystems #HealthInformatics
https://arxiv.org/abs/2610.16108
#ClinicalAI #MultiAgentSystems #HealthInformatics
https://arxiv.org/abs/2610.16108
October 14, 2026 at 4:01 PM
GUIDE is a multi-agent system that helps experts update clinical practice guidelines, reaching around 88.85% recall and over 91% recommendation agreement on ophthalmology and other specialty datasets, with under…
#ClinicalAI #MultiAgentSystems #HealthInformatics
https://arxiv.org/abs/2610.16108
#ClinicalAI #MultiAgentSystems #HealthInformatics
https://arxiv.org/abs/2610.16108
Multi-agent delegation should narrow authority by task, tenant, tool, resource, time, and budget. A handoff is not permission inheritance. #multiagentsystems
Do Not Give Every Sub Agent the Parent's Tool Belt
hackernoon.com
October 11, 2026 at 7:58 PM
Multi-agent delegation should narrow authority by task, tenant, tool, resource, time, and budget. A handoff is not permission inheritance. #multiagentsystems
Reward hacking can spread between agents in multi-agent coding systems, amplifying a behavior meant to be a single-agent failure into a coordination problem. Across four open-weight backbones, RL training…
#OpenSourceAI #MultiAgentSystems #AIRL #MachineLearning
https://arxiv.org/abs/2610.12822
#OpenSourceAI #MultiAgentSystems #AIRL #MachineLearning
https://arxiv.org/abs/2610.12822
October 12, 2026 at 8:01 AM
Reward hacking can spread between agents in multi-agent coding systems, amplifying a behavior meant to be a single-agent failure into a coordination problem. Across four open-weight backbones, RL training…
#OpenSourceAI #MultiAgentSystems #AIRL #MachineLearning
https://arxiv.org/abs/2610.12822
#OpenSourceAI #MultiAgentSystems #AIRL #MachineLearning
https://arxiv.org/abs/2610.12822
The MASS system optimizes multi-agent workflows and distills collective intelligence to serve as a self-supervision signal, improving scores per output token on research benchmarks.
#RecursiveSelfImprovement #MultiAgentSystems #CollectiveIntelligence
#RecursiveSelfImprovement #MultiAgentSystems #CollectiveIntelligence
MASS improves score per output token on research benchmarks
Source: HackerNews front
realfeedapp.com
October 12, 2026 at 6:00 AM
The MASS system optimizes multi-agent workflows and distills collective intelligence to serve as a self-supervision signal, improving scores per output token on research benchmarks.
#RecursiveSelfImprovement #MultiAgentSystems #CollectiveIntelligence
#RecursiveSelfImprovement #MultiAgentSystems #CollectiveIntelligence
One AI agent's hallucination can influence an entire multi-agent system. Explore semantic blast radius, error propagation, and ways to contain unreliable info. #multiagentsystems
Semantic Blast Radius: How Errors Propagate Through Multi-Agent Systems
hackernoon.com
October 9, 2026 at 8:40 AM
One AI agent's hallucination can influence an entire multi-agent system. Explore semantic blast radius, error propagation, and ways to contain unreliable info. #multiagentsystems
Two agent systems can fail identically in the trace and differently in fact. 'Know the Shape, Find the Fault' lifts failure-diagnosis accuracy from 0.17 to 0.35 by conditioning on how the agents were wired to talk. Structure is evidence. #MultiAgentSystems #AIEngineering
October 8, 2026 at 7:00 PM
Two agent systems can fail identically in the trace and differently in fact. 'Know the Shape, Find the Fault' lifts failure-diagnosis accuracy from 0.17 to 0.35 by conditioning on how the agents were wired to talk. Structure is evidence. #MultiAgentSystems #AIEngineering
What happens when AI agents work as a team? Multi-agent systems split complex tasks across specialized agents, but costs and coordination matter.
See how they work and when they make sense:
aitransformer.online/multi-agent-...
#AIAgents #MultiAgentSystems
See how they work and when they make sense:
aitransformer.online/multi-agent-...
#AIAgents #MultiAgentSystems
Multi-Agent Systems Explained - AI Transformer Online
Multi-agent systems split big AI jobs across teams of agents. See how they work, what they cost, and why many of them fail today.
aitransformer.online
October 8, 2026 at 2:31 PM
What happens when AI agents work as a team? Multi-agent systems split complex tasks across specialized agents, but costs and coordination matter.
See how they work and when they make sense:
aitransformer.online/multi-agent-...
#AIAgents #MultiAgentSystems
See how they work and when they make sense:
aitransformer.online/multi-agent-...
#AIAgents #MultiAgentSystems
A new arXiv paper proposes a heterogeneous Graph Neural Network framework for generating and evaluating shared roadmaps in multi-agent path planning, aiming to improve safety and efficiency in…
#AIResearch #MultiAgentSystems #PathPlanning #MachineLearning
https://arxiv.org/abs/2610.09034
#AIResearch #MultiAgentSystems #PathPlanning #MachineLearning
https://arxiv.org/abs/2610.09034
October 8, 2026 at 8:01 AM
A new arXiv paper proposes a heterogeneous Graph Neural Network framework for generating and evaluating shared roadmaps in multi-agent path planning, aiming to improve safety and efficiency in…
#AIResearch #MultiAgentSystems #PathPlanning #MachineLearning
https://arxiv.org/abs/2610.09034
#AIResearch #MultiAgentSystems #PathPlanning #MachineLearning
https://arxiv.org/abs/2610.09034
Cornerstone OnDemand's Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, cut database diagnosis from 45…
#AI #DatabaseAutomation #AWS #MultiAgentSystems
https://aws.amazon.com/blogs/machine-learning/how-cornerstone-ondemand-cut-database-diagnosis-by-78-with-amazon-bedrock/
#AI #DatabaseAutomation #AWS #MultiAgentSystems
https://aws.amazon.com/blogs/machine-learning/how-cornerstone-ondemand-cut-database-diagnosis-by-78-with-amazon-bedrock/
October 7, 2026 at 4:01 PM
Cornerstone OnDemand's Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, cut database diagnosis from 45…
#AI #DatabaseAutomation #AWS #MultiAgentSystems
https://aws.amazon.com/blogs/machine-learning/how-cornerstone-ondemand-cut-database-diagnosis-by-78-with-amazon-bedrock/
#AI #DatabaseAutomation #AWS #MultiAgentSystems
https://aws.amazon.com/blogs/machine-learning/how-cornerstone-ondemand-cut-database-diagnosis-by-78-with-amazon-bedrock/
MATE is a new multi-agent reinforcement learning method that uses visual attention on salient objects to help AI agents coordinate with unseen partners zero-shot. Unlike symmetry-breaking, it…
#AI #ReinforcementLearning #MultiAgentSystems #ZeroShotCoordination
https://arxiv.org/abs/2610.06025
#AI #ReinforcementLearning #MultiAgentSystems #ZeroShotCoordination
https://arxiv.org/abs/2610.06025
October 6, 2026 at 4:01 PM
MATE is a new multi-agent reinforcement learning method that uses visual attention on salient objects to help AI agents coordinate with unseen partners zero-shot. Unlike symmetry-breaking, it…
#AI #ReinforcementLearning #MultiAgentSystems #ZeroShotCoordination
https://arxiv.org/abs/2610.06025
#AI #ReinforcementLearning #MultiAgentSystems #ZeroShotCoordination
https://arxiv.org/abs/2610.06025
New work on multi-agent safety proposes authorization-paired evaluation, cutting denied-commit rates from 86.0% to zero in controlled composition experiments without losing authorized supply. FlowReview ties object…
#AI #CyberSecurity #AISafety #MultiAgentSystems
https://arxiv.org/abs/2610.00371
#AI #CyberSecurity #AISafety #MultiAgentSystems
https://arxiv.org/abs/2610.00371
October 2, 2026 at 10:01 PM
New work on multi-agent safety proposes authorization-paired evaluation, cutting denied-commit rates from 86.0% to zero in controlled composition experiments without losing authorized supply. FlowReview ties object…
#AI #CyberSecurity #AISafety #MultiAgentSystems
https://arxiv.org/abs/2610.00371
#AI #CyberSecurity #AISafety #MultiAgentSystems
https://arxiv.org/abs/2610.00371