From LLMs to AI Agents — 25 Papers on Agentic Workflows
Comprehensive survey of 25 landmark papers tracing the evolution from simple LLM workflows to autonomous agentic systems and multi-agent architectures.
2026 update note
Older publish date · context add-on
Editorial note for 2026. This does not replace the historical article below.
- Prefer current official docs for frameworks, APIs, and package names; sample code here is mostly pedagogical—check release notes when migrating.
- Llama / RAG / Prompt ecosystems move fast; pair this post with 2026 articles and the tools directory on this site.
- If you spot factual drift, reach out via the footer—we will refresh this note or spin up a follow-up post.
Recent picks: Observability · Graph RAG · Prompting & tools · Small-model deployment
From LLMs to AI Agents — 25 Papers
Reasoning
CoT (Wei 2022): Reasoning steps improve problem-solving. ToT (Yao 2023): Branching search over reasoning paths.
Tool Use
Toolformer (Schick 2023): Self-supervised tool learning. Gorilla: Fine-tuned for API call generation.
Agents
ReAct (Yao 2022): Synergistic reasoning and acting. AutoGPT: Autonomous task decomposition. MetaGPT: Multi-agent software company simulation. CrewAI: Role-based agent team orchestration.
Multi-Agent
ChatDev, AutoGen, AgentVerse — multi-agent conversation frameworks improving on single-agent by 20-40%.
Safety
Constitutional AI, RLHF, InstructGPT — alignment foundations.
Key Insight
Tool-use reliability is the primary bottleneck. Current agents fail on 15-30% of API calls.
Related Content
Articles
Distributed Training Techniques for Large Language Models
Comprehensive survey of distributed LLM training approaches including data parallelism, tensor parallelism, pipeline parallelism, and ZeRO optimization.
Read moreArchitecture Guide for Building an LLM Application Platform
Comprehensive architectural overview of designing and deploying a production LLM application platform covering RAG, agent systems, and monitoring.
Read moreVectorGraph — Ant Group Open-Source GraphRAG Framework Analysis
Design philosophy and technical architecture of VectorGraph, Ant Group first open-source GraphRAG framework for knowledge-enhanced LLM applications.
Read moreRelated Tools
chatgpt
Conversational AI assistant by OpenAI for real-time code generation, debugging, and technical problem-solving through natural language interaction.
View toolWindsurf
Codeium AI-native IDE with Cascade agentic flow, multi-file editing, deep codebase indexing, and real-time collaborative AI assistance.
View toolClaude Code
Anthropic's terminal-native AI coding agent that operates directly on your codebase with file editing, shell command execution, and Git integration.
View toolRelated Workflows
AI-Powered Code Review Workflow
Use AI tools to automate and improve your code review process
View workflowBuilding with MCP: Server Development Workflow
Step-by-step workflow for creating and deploying MCP servers
View workflowChatGPT Prompt Engineering Workflow
Master prompt engineering techniques to get the best results from ChatGPT
View workflow