SALT-NLP/DyLAN

Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

43
/ 100
Emerging

This project helps researchers and AI practitioners improve the accuracy and efficiency of complex tasks like mathematical reasoning and code generation when using large language models (LLMs). It takes a query or problem as input and dynamically assigns the most effective team of LLM agents to collaborate and arrive at a solution. The output is a highly accurate answer or generated code, with the end-user being anyone working with LLMs on challenging analytical or programming problems.

196 stars. No commits in the last 6 months.

Use this if you need to tackle complex reasoning or code generation tasks with LLMs and find that single LLM executions are insufficient, or that existing multi-agent systems require too much manual configuration.

Not ideal if you're dealing with simple, straightforward LLM tasks that a single model can handle effectively, or if you prefer a fixed, transparent multi-agent architecture.

AI research LLM applications complex reasoning code generation agent systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

196

Forks

27

Language

Python

License

MIT

Last pushed

May 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/SALT-NLP/DyLAN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.