20 papers across 6 areas to master production-grade agentic AI engineering
MaryamMiradi · x · 2026-10-27
Maryam Miradi curated 20 research papers for mastering production AI agent engineering, organized into 6 areas:
- Reasoning/planning/tool use: ReAct, Toolformer, LATS, Reflexion, Self-Refine
- Memory & lifelong learning: Generative Agents, MemGPT, Voyager
- Multi-agent orchestration: AutoGen, MetaGPT
- Knowledge & retrieval: RAG, Self-RAG, CRAG
- Execution & evaluation: SWE-agent, SWE-bench, WebArena, AgentBench, τ-bench
- Reliability & security: AgentDojo (prompt injection), AI Agents That Matter
Her takeaway: knowing frameworks ≠ agentic engineering — understanding reasoning, memory, retrieval, evaluation, and security is what makes agents actually work in production. The image maps all papers with arXiv links.
More from coding & agent
- For OSS apps, proofs of concept — not PRs to one repo — may be the core primitive — dbreunig · 2026-10-27
- Hook everything into the Dot: a workaround to stretch ChatGPT subscription limits — teortaxesTex · 2026-10-27
- Jev launches people-search API for agents at $0.0089/lead, claiming 85% cheaper than Clay — alexcovo_eth · 2026-10-27
- Going through every compound engineering skill to decide where humans stay in the loop — kieranklaassen · 2026-10-27
- UCSB CS Prof. Xifeng Wang lands 3 grants worth $180K+ for practical agentic AI research — xwang_lk · 2026-10-27
- Gen games don't need to be realtime — turn-based interactivity works, devs argue — djcows · 2026-10-27