DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Paper
•
2310.03714
•
Published
•
30
🤖 Agents
Note I'm not a fan of the implementation, but I think the ideas behind DSPy are interesting.
-
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 35
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 3Note The paper that introduced the concept of multi-agents!
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 183Note GAIA benchmark is the most challenging benchmark for generalist agents, requiring a good web browser, multimodal capabilities, and complex multi-step task solving.
-
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 109 -
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Paper • 2402.07456 • Published • 41 -
Self-Refine: Iterative Refinement with Self-Feedback
Paper • 2303.17651 • Published • 2 -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 4 -
Gorilla: Large Language Model Connected with Massive APIs
Paper • 2305.15334 • Published • 4 -
MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
Paper • 2303.11381 • Published • 2 -
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace
Paper • 2303.17580 • Published • 9 -
Communicative Agents for Software Development
Paper • 2307.07924 • Published • 3 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 51
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 14Note This paper is the basis for the Thought -> Action -> Observation cycle used in most agent frameworks nowadays.
-
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 27 -
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Paper • 2310.06770 • Published • 4