ZichengXu/Decoding-Tree-Sketching
Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.
This project helps AI researchers and practitioners improve the accuracy and efficiency of their large language models (LLMs) when solving complex reasoning tasks, like math problems or scientific queries. You input a prompt into your existing reasoning model, and this framework processes its output to deliver a more accurate and concise answer. It's designed for those who work with or deploy LLMs and need them to perform better on intricate logical challenges.
Use this if you are an AI researcher or machine learning engineer looking to significantly boost the reasoning accuracy of your existing large language models without additional training, especially for complex problem-solving.
Not ideal if you are a general user looking for an out-of-the-box application for everyday tasks or if you do not have experience working with LLMs at a technical level.
Stars
67
Forks
11
Language
Python
License
MIT
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/ZichengXu/Decoding-Tree-Sketching"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models