XMUDeepLIT/TTCS
The code implementation for TTCS: Test-Time Curriculum Synthesis for Self-Evolving.
This framework helps AI researchers and machine learning engineers significantly improve the mathematical reasoning abilities of large language models (LLMs) without needing new training data or human feedback. It takes an existing LLM and mathematical problems as input, then iteratively refines the LLM's problem-solving capabilities by dynamically generating and learning from related, simpler problem variations. The output is a more robust and accurate LLM for mathematical tasks.
Use this if you need to boost the mathematical reasoning performance of your LLMs on specific test problems, especially when fine-tuning with external data or human-labeled examples is impractical or costly.
Not ideal if you are looking for a general-purpose LLM improvement method not specifically focused on mathematical reasoning or if you lack access to GPU resources for training.
Stars
39
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/XMUDeepLIT/TTCS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is...
sotopia-lab/sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
zhudotexe/redel
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive...
TIGER-AI-Lab/verl-tool
A version of verl to support diverse tool use
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning