AndresCotton/agentic-eval-multi-participant-coordination

View on GitHub ↗

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).

3 ★2 forksPythonUpdated 10mo ago

Topics

agent-orchestrationai-agentsai-benchmarkinglangchainlanggraphllm-evaluationmcpmodel-context-protocolmulti-agent-systemsnlp
Stars
3★
Forks
2
Language
Python
License
NOASSERTION
Created
2025-06-09
Last push
2025-10-27