Tagged articles
3 articles
Page 1 of 1
o-ai.tech
o-ai.tech
Apr 17, 2026 · Artificial Intelligence

How Hermes Agent Self‑Evolves: Memory, Skills, and Offline Training Pipelines

This article dissects Hermes Agent’s self‑evolution mechanism, explaining how stable facts are stored in memory, reusable procedures become skills, and rollout trajectories are turned into training data through background review, context compression, and OPD‑based token‑level distillation.

Agent ArchitectureContext CompressionHermes Agent
0 likes · 33 min read
How Hermes Agent Self‑Evolves: Memory, Skills, and Offline Training Pipelines
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Feb 24, 2026 · Artificial Intelligence

Optimizing Structured Processes in the Large‑Model Era: From Reasoning to Agentic RL

The article analyzes how large‑model development has moved from reasoning to the agentic stage, compares open‑source and closed‑source capabilities, details Reasoning RL versus Agentic RL designs, and proposes skill‑centric data and verification mechanisms to close the performance gap.

DeepSeekGLM-5Large Language Models
0 likes · 10 min read
Optimizing Structured Processes in the Large‑Model Era: From Reasoning to Agentic RL