iiis-ai/cumulative-reasoning
[TMLR] Cumulative Reasoning With Large Language Models (https://arxiv.org/abs/2308.04371)
This project offers a structured way to guide large language models (LLMs) to solve complex problems by breaking them down, checking each step, and then combining the valid parts. It takes a problem statement or question as input and produces a robust, verified solution, especially useful for challenging mathematical or logical puzzles. This is for anyone who uses advanced AI models for intricate problem-solving, like researchers or data scientists working with complex computational tasks.
308 stars. No commits in the last 6 months.
Use this if you need to improve the accuracy and reliability of large language models when solving multi-step reasoning problems, particularly in mathematics or logical puzzles.
Not ideal if your problems are simple and require quick, straightforward answers without complex validation steps.
Stars
308
Forks
35
Language
Python
License
—
Category
Last pushed
Aug 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/iiis-ai/cumulative-reasoning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
sapientinc/HRM
Hierarchical Reasoning Model Official Release
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models