Resources
Curated research papers, frameworks, protocols, and tools for the practitioner.
Research Papers
Foundational
Introduces the ReAct paradigm combining reasoning traces with actions.
Demonstrates self-supervised tool use learning in LLMs.
Foundational work on prompting LLMs for step-by-step reasoning.
Extends CoT with exploration of multiple reasoning paths.
Memory
Agents with memory for believable social simulation.
Hierarchical memory management for unbounded context.
Agents that learn from self-reflection and memory.
Multi-Agent
Framework for multi-agent conversation and collaboration.
Role-based multi-agent system for software development.
Multiple agents debate to improve reasoning quality.
RAG
Original RAG paper combining retrieval with generation.
Agents that decide when and what to retrieve.
Self-correcting retrieval with web search fallback.
Knowledge graph-based RAG for complex queries.
Safety
Self-supervision for safe AI behavior.
Automated red teaming for safety evaluation.
Frameworks
Framework for LLM-powered applications. Large ecosystem of integrations.
Stateful, multi-actor applications with LLMs. Graph-based control flow.
Unifying AutoGen and Semantic Kernel for multi-agent workflows.
Protocols
Anthropic's open protocol for connecting AI with tools and data sources.
Google's protocol for agent-to-agent communication and discovery.
Open standard for agentic commerce from discovery to purchase.
Evaluation Tools
Open-source evaluation framework for LLMs. Agent-specific metrics.
Evaluation framework for RAG applications. Component-level metrics.
CLI tool for testing and evaluating prompts. CI/CD integration.
Platform for debugging, testing, and monitoring LLM applications.
Enterprise platform for AI product development. Evals and logging.