Lanerra/reasoning-bank-slm
An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much smaller, less capable models.
This project helps AI developers and researchers make small language models smarter at complex reasoning tasks like solving math problems. It does this by giving the model a 'memory' where it stores successful and unsuccessful problem-solving strategies. When faced with a new problem, the model retrieves relevant strategies from its memory to guide its decision-making, leading to improved performance with less computational cost.
No commits in the last 6 months.
Use this if you are a developer or researcher working with small language models (under 4 billion parameters) and need to improve their reasoning capabilities without scaling up model size.
Not ideal if you are working with very large language models or are not interested in memory-based self-improvement techniques.
Stars
99
Forks
13
Language
Python
License
—
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Lanerra/reasoning-bank-slm"
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