tree-of-thoughts 开源项目推荐（65 个）

kyegomez /swarms

企业级多智能体编排框架。网站：https://swarms.ai

princeton-nlp /tree-of-thought-llm

[NeurIPS 2023] 思维树：用大语言模型进行审慎的问题求解

satellitecomponent /Neurite

思想的分数形图。人工智能代理、网络链接、注释和代码的根形思维导图。

OpenDriveLab /DriveLM

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

jieyilong /tree-of-thought-puzzle-solver

The Tree of Thoughts (ToT) framework for solving complex reasoning tasks using LLMs

kyegomez /the-compiler

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

skymanbp /cc-tree

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

guilt /TinyToT

TinyToT — Tree of Thoughts inference server

fblgit /tree-of-knowledge

ToK aka Tree of Knowledge for Large Language Models LLM. It's a novel dataset that inspires knowledge symbolic correlation in simple input and output prompts

th0r3nt /JAWL

Framework for building continuous-loop autonomous AI agents.

om-ai-lab /open-agent-leaderboard

Reproducible Language Agent Research

JRC1995 /ZeroPromptSearch

Implementation of an LLM prompting pipeline combined with wrappers for auto-decomposing reasoning steps and for search through the reasoning-step-space (eg. by beam search, MCTS etc.) guided by self-evaluation.

ictup /Enhancing-QA-Systems-through-Integrated-Reasoning-over-Knowledge-Bases-and-Large-Language-Models

KG-RAG + ToT + multi-agent LLMs for evidence-grounded QA with Neo4j and fine-tuning; reproducible medical case study & evaluation.

dtunai /SynthToT

SynthToT: Generate synthetic dataset for your training dataset through deliberate problem-solving et al S Yao, 2023.

reasonkit /reasonkit-core

The Reasoning Engine — Auditable Reasoning for Production AI | Rust-Native | Turn Prompts into Protocols

FradSer /dialectica

An adversarial reasoning engine — a pluggable tree-search workflow where thoughts are generated, adversarially evaluated (GAN-style), and synthesized. Thesis → antithesis → synthesis.

shtse8 /DeepResearch

Advanced AI-powered research tool with human-like reasoning capabilities. Implements Tree of Thoughts and ReAct methodologies for deep, multi-step research.

sunnybedi990 /reasonchain

A modular AI reasoning library for creating intelligent agents with advanced reasoning pipelines, memory management, and seamless LLM integration.

yifu-ding /DPTS

Official implementation of Dynamic Parallel Tree Search for accelerating LLM reasoning with test-time parallel search.

safouaneelg /zeroshot-reasoning

Ollama structured output for visual zeroshot reasoning