Loading connector details…
Agentic Eval Multi Participant Coordination
MCPOpen SourceNOASSERTION16.2
by AndresCotton • Uncategorized
AI agent evaluation framework for multi-participant coordination tasks. Built with LangGraph, custom MCP tools, and LLM-as-a-Judge evaluation. MSc dissertation project (University of Edinburgh, 2025).
Description
AI agent evaluation framework for multi-participant coordination tasks. Built with LangGraph, custom MCP tools, and LLM-as-a-Judge evaluation. MSc dissertation project (University of Edinburgh, 2025).
Quick Actions
Quick Stats
Service TypeMCP
Pricing ModelFree
Capabilities0 Tools / 0 Prompts / 0 Resources
OwnerAndresCotton
CategoryUncategorized
Tags
agent-orchestrationai-agentsai-benchmarkinglangchainlanggraphllm-evaluationmcpmodel-context-protocolmulti-agent-systemsnlp