AgentR A Stateful and Recovery-Aware Software Architecture for LLM-based Auditable Workflows
Source
Riya Samanta, Bidyut Saha, Soumya Kanti Ghosh, Rajkumar Buyya
Author
Riya Samanta, Bidyut Saha, Soumya Kanti Ghosh, Rajkumar Buyya
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Most AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → applications are still stateless prompt-response wrappers, and this lays out what has to exist for one to survive interruption and stay auditable.
articleLegacyWorld: Atomicity-Aware Evaluation of GUI Agents for Legacy WorkflowsThilo Reintjes, Sivajeet Chand, Derui Zhu, Sushant Kumar Pandey, Alexander Pretschner
articleAgentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration TestingIsrat Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
articleSupporting Industrial Test-Failure Analysis with LLM-Based Systems: An Experience ReportEric Jansson, Per Strandberg, Thomas S\"orensen, Eduard Paul Enoiu, Wasif Afzal