bytedance/deer-flow
DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.
Awesome AI Agents › Reasoning Frameworks
lafmdp/Awesome-Papers-Autonomous-Agent
The project "Awesome-Papers-Autonomous-Agent" is a curated and actively maintained collection of recent academic papers focused on the development of autonomous agents in artificial intelligence. Autonomous agents are defined as systems that perceive their environment, take autonomous actions to achieve goals, acquire knowledge, and continually improve their performance. This repository specifically emphasizes two main categories of autonomous agents: those based on Reinforcement Learning (RL) and those leveraging Large Language Models (LLMs). The collection excludes traditional RL agents and instead highlights cutting-edge research that integrates RL and LLM approaches. It includes papers from top-tier conferences such as ICML, ICLR, and NeurIPS, covering a wide range of topics including instruction following, world model-based agents, language as knowledge, LLMs as tools, generalization across tasks, continual learning, and the combination of RL and LLM techniques. The repository also features surveys that provide comprehensive overviews of LLM-based autonomous agents. The papers are systematically categorized to facilitate easy navigation and understanding of the field's current trends and innovations. Categories include multimodal agents, task-specific designs, multi-agent systems, experimental analyses, benchmarks and datasets, applications, and algorithm design. The repository also links to project pages and code repositories when available, enhancing its utility as a resource for researchers and practitioners. This project serves as a valuable resource for anyone interested in the latest advancements in autonomous agent research, providing a centralized hub of knowledge that supports ongoing learning and development in this rapidly evolving area of AI. It encourages community contributions to keep the collection comprehensive and up-to-date.
https://github.com/lafmdp/Awesome-Papers-Autonomous-Agent
Also in Reasoning Frameworks
VectifyAI/PageIndex
PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.
guidance-ai/guidance
Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.
friuns2/BlackFriday-GPTs-Prompts
A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.
refly-ai/refly
Refly is an open-source AI-native creation engine that combines multi-threaded dialogues, multimodal inputs, knowledge base integration, and AI-powered tools to transform ideas into production-ready interactive content and web applications.
mongodb-developer/GenAI-Showcase
MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.
anysphere/priompt
Priompt is a JSX-based prompting library that uses a priority system to efficiently construct token-limited prompts for language models, inspired by React's component design.
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, fully automated, and cost-effective personal AI assistant that supports multiple large language models and offers a one-click launch experience as an alternative to OpenAI's Deep Research.