- Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
- CHAIN-OF-VERIFICATION REDUCES HALLUCINATION IN LARGE LANGUAGE MODELS
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
- LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
- Better Zero-Shot Reasoning with Self-Adaptive Prompting
- FNet: Mixing Tokens with Fourier Transforms
- TransformerFAM: Feedback attention is working memory
- HiPPO: Recurrent Memory with Optimal Polynomial Projections
- Reducing Activation Recomputation in Large Transformer Models
- Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
- More Agents Is All You Need
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation
- KAN: Kolmogorov–Arnold Networks
- xLSTM: Extended Long Short-Term Memory
- HGRN2: Gated Linear RNNs with State Expansion
- The original BabyAGI from March 2023 introduced task planning as a method for developing autonomous agents
- BabyBeeAGI: Task Management and Functionality Expansion on top of BabyAGI
- Letta (previously MemGPT) is an open source framework for building stateful LLM applications. You can use Letta to build stateful agents with advanced reasoning capabilities and transparent long-term memory
- MiniAGI is a simple autonomous agent compatible with GPT-3.5-Turbo and GPT-4. It combines a robust prompt with a minimal set of tools, chain-of-thoughts, and short-term memory with summarization. It is also capable of inner monologue and self-criticism
- Teenage-AGI, Inspired by several Auto-GPT-related Projects (predominantly BabyAGI)
- WorkGPT is an agent framework in a similar fashion to AutoGPT or LangChain
- Awesome Agents is a curated list of open source AI agents
- A collection of autonomous agents 🤖️ powered by LLM
- We introduce a novel LLM-based multimodal agent framework designed to operate smartphone applications