Remote AI Paper Discussion Group

Link to articles: 1. digestable introduction: https://www.dailydoseofds.com/p/hermes-agent-masterclass/ 2. the source of truth: https://github.com/NousResearch/hermes-agent-self-evolution/blob/main/PLAN.md
Title: Hermes Agent Masterclass & Plan.md
Track: Self-Improving LLM Agents
Content: The first document presents Hermes as a self-improving open-source agent combining persistent memory, reusable self-written skills, automatic skill curation, and offline GEPA optimization. It also explains how to configure isolated specialist agents—with distinct identities, tools, Telegram bots, and scheduled jobs—on your own machine. The second document specifies a separate pipeline that uses DSPy/GEPA to evolve Hermes Agent’s skills, tool descriptions, and prompts, with Darwinian Evolver handling code changes: development proceeds through five gated phases—from skill optimization to continuous self-improvement—with benchmarks, tests, human-reviewed PRs, and rollback safeguards preventing regressions.
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.