[PDG 497] Self-Improvements in Modern Agentic Systems: A Survey

Link to article: https://arxiv.org/pdf/2607.13104
Title: Self-Improvements in Modern Agentic Systems: A Survey
Track: Self-Improving LLM Agents
Content: Self-improving agents are adaptive systems that convert experience into lasting capability gains by updating either a foundation model or its operational scaffold, including prompts, memory, tools, and control logic. The survey classifies existing approaches by what they update and which signals drive improvement, then examines applications, evaluation methods, open challenges, and future directions.
Slack link: ml-ka.slack.com, channel: #pdg. Please join us -- if you cannot join, please message us here or to mlpaperdiscussiongroupka@gmail.com.

In the Paper Discussion Group (PDG) we discuss recent and fundamental papers in the area of machine learning on a weekly basis. If you are interested, please read the paper beforehand and join us for the discussion. If you have not fully understood the paper, you can still participate – everyone is welcome! You can join the discussion or simply listen in. The discussion is in German or English depending on the participants.