Tagged articles

Self-Evolving Skills

4 articles · Page 1 of 1

May 31, 2026 · Artificial Intelligence

Microsoft’s SkillOpt Turns Agent Skill Docs into Trainable Parameters for Self‑Evolving AI

Microsoft’s newly open‑source SkillOpt framework treats an agent’s skill document as external weights, applying a rollout‑reflect‑edit‑gate training loop with textual learning rates and rejected‑edit buffers, enabling self‑evolving skills that achieve optimal or tied‑optimal results across 52 model‑benchmark‑environment combinations.

AI agentsMicrosoftSelf-Evolving Skills

0 likes · 12 min read

Microsoft’s SkillOpt Turns Agent Skill Docs into Trainable Parameters for Self‑Evolving AI

Tech Ocean

May 23, 2026 · Artificial Intelligence

Building Self-Evolving AI Skills: A Harness Engineering Case Study with SkillForge

The article explores Harness Engineering as a framework for creating reliable, long‑running AI agents, detailing a hands‑on project called SkillForge that transforms books into executable Skills, and outlines key components, iterative processes, documentation, and best practices for stable, self‑evolving AI workflows.

AI agentsAgentic WorkflowHarness Engineering

0 likes · 20 min read

Building Self-Evolving AI Skills: A Harness Engineering Case Study with SkillForge

SuanNi

May 10, 2026 · Artificial Intelligence

Hermes Agent Overtakes OpenClaw to Lead Global Token Consumption

Hermes Agent, an open‑source autonomous‑agent framework from Nous Research, has surpassed OpenClaw to become the top token consumer on OpenRouter, offering self‑evolving skills, persistent cross‑session memory, multi‑environment execution, and extensive IM integration while addressing security and deployment challenges.

AI agentsHermes AgentOpenClaw

0 likes · 7 min read

Hermes Agent Overtakes OpenClaw to Lead Global Token Consumption

Alibaba Cloud Big Data AI Platform

Apr 2, 2026 · Artificial Intelligence

How Alibaba Cloud’s Ops‑Agentic‑Search Reached Human‑Level Performance on the GAIA Benchmark

The article explains the shift of AI agents from passive responders to proactive executors, outlines the challenges of hallucination, task failure, and consistency, introduces the GAIA benchmark, and details how Alibaba Cloud's Ops‑Agentic‑Search achieved a 92.36% accuracy—matching human experts—through global planning, reflection, dynamic context management, and a self‑evolving skills system.

AI AgentDynamic PlanningEnterprise AI

0 likes · 12 min read