fannie1208/W4S
[COLM2025] "Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors"
This project helps AI developers and researchers efficiently create and optimize complex AI workflows. It takes a 'weak' meta-agent's high-level instructions and uses a 'strong' AI model to generate and refine executable Python code for a specific task. The output is an improved, robust workflow that leverages the strong model's capabilities, ideal for those building sophisticated AI systems.
No commits in the last 6 months.
Use this if you need to automate the design and optimization of workflows for powerful AI models, allowing a less capable 'agent' to effectively orchestrate a more capable 'executor'.
Not ideal if you are looking for a plug-and-play solution for a simple, predefined AI task or if you are not comfortable working with AI agent frameworks and Python code.
Stars
55
Forks
3
Language
Python
License
—
Category
Last pushed
Oct 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/fannie1208/W4S"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...