zou-group/sirius

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

44
/ 100
Emerging

This project helps researchers and developers create AI systems that can learn and improve their reasoning over time, similar to how humans learn from experience. It takes initial problem descriptions or game scenarios, along with agent interactions, and produces improved, more accurate AI agents. This is ideal for those building sophisticated AI agents for tasks like complex problem-solving, iterative refinement of answers, or strategic competitive interactions.

Use this if you need AI agents that can continuously get better at tasks by learning from their past successes and failures.

Not ideal if you are looking for a pre-built, ready-to-deploy AI solution without custom agent development or model fine-tuning.

AI agent development complex problem solving iterative refinement game theory reasoning systems
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

98

Forks

11

Language

Python

License

MIT

Last pushed

Dec 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zou-group/sirius"

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