AI:tools

LLM

Open-weights LLM

• Nemetron-4 340B

Cloud LLM

• Groq cloud (very fast inference)

Multi-modal: Audio

• kyutai Open Science AI Lab chatbot moshi

Triage

• RouteLLM: Learning to Route LLMs with Preference Data

Retrieval Augmented Generation (RAG)

• GraphRAG (preprint, code)

Automatic Optimization

Analogous to Gradient Descent

• TextGrad: Automatic "Differentiation" via Text
• Symbolic Learning Enables Self-Evolving Agents

LLM for scoring/ranking

• GPTScore: Evaluate as You Desire
• Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
• Domain-specific chatbots for science using embeddings
• Large Language Models as Evaluators for Scientific Synthesis

LLM Agents

Multi-agent orchestration

Research demos

• Camel
• LoopGPT
• JARVIS
• OpenAGI
• AutoGen
• TaskWeaver
• MetaGPT

Architectures

• Mixture-of-Agents Enhances Large Language Model Capabilities

Cloud solutions

• Numbers Station Meadow: agentic framework for data workflows (code).
• CrewAI says they provide multi-agent automations (code).
• LangChain introduced LangGraph to help build agents, and LangGraph Cloud as a service for running those agents.

Optimization

Metrics, Benchmarks

• AI Agents That Matter

Evolution Improvement

• EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

Text-to-speech (TTS)

Open Source

• Parler TTS
• Toucan (demo)
• MetaVoice (github)
• ChatTTS
• Camb.ai MARS5-TTS

Cloud

• Elevenlabs
  • voice isolator
• Cartesia Sonic

Conversational Audio Chatbot

• Swift is a fast AI voice assistant (code, live demo) uses:
  • Groq cloud running OpenAI Whisper for fast speech transcription.
  • Cartesia Sonic for fast speech synthesis
  • VAD to detect when user is talking
  • Vercel for app deployment
• kyutai Moshi chatbot (demo)

Vision

• Supervision
• Florence-2