<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent on Watchstep Blog</title><link>https://blog.watchstep.site/categories/agent/</link><description>Recent content in Agent on Watchstep Blog</description><generator>Hugo</generator><language>en</language><copyright>Â©Â 2025 watchstep</copyright><lastBuildDate>Wed, 08 Apr 2026 12:07:49 +0900</lastBuildDate><atom:link href="https://blog.watchstep.site/categories/agent/index.xml" rel="self" type="application/rss+xml"/><item><title>🗃️ Meta-Harness : End-to-End Optimization of Model Harnesses (2026-03) 논문 리뷰</title><link>https://blog.watchstep.site/posts/meta-harness/</link><pubDate>Wed, 08 Apr 2026 12:07:49 +0900</pubDate><guid>https://blog.watchstep.site/posts/meta-harness/</guid><description>&lt;p>본 글은 &lt;strong>&lt;a href="https://yoonholee.com/meta-harness/">Meta-Harness: End-to-End Optimization of Model Harnesses&lt;/a>&lt;/strong> 논문 리뷰 글이다.&lt;/p>
&lt;h2 id="0-harness">0/ Harness&lt;/h2>
&lt;img width="500" height="auto" alt="AI Engineering Harness의 개념을 말과 안장 비유로 설명한 그림" src="image_1.png" />
&lt;p>&lt;a href="https://strategizeyourcareer.com/p/harness-engineering-ai-agents">https://strategizeyourcareer.com/p/harness-engineering-ai-agents&lt;/a>&lt;/p></description></item><item><title>🏇 Harness Engineering for coding agents</title><link>https://blog.watchstep.site/posts/harness_engineering/</link><pubDate>Sun, 05 Apr 2026 20:02:02 +0900</pubDate><guid>https://blog.watchstep.site/posts/harness_engineering/</guid><description>&lt;h2 id="0-harness-engineering">0/ Harness Engineering&lt;/h2>
&lt;img width="500" height="auto" alt="" src="image_1.png" />
&lt;p>Harness는 모델을 둘러싼 모든 외부 환경으로, 시스템 프로프트, 파일 시스템, 모델 라우팅, 외부 도구 등 모델 바깥에서 동작하는 시스템 전체를 의미한다.
(모델이 🐴 말이면 harness는 말이 마차를 잘 끌 수 있도록 사용하는 마구.)&lt;/p></description></item><item><title>🎱 Effective context engineering for AI agents (Anthropic, 2025-09-29) 리뷰</title><link>https://blog.watchstep.site/posts/effective_context_engineering_anthropic/</link><pubDate>Mon, 13 Oct 2025 12:06:53 +0900</pubDate><guid>https://blog.watchstep.site/posts/effective_context_engineering_anthropic/</guid><description>&lt;h1 id="ai-에이전트의-성능을-극대화하기-위한-효과적인-컨텍스트-엔지니어링-전략">AI 에이전트의 성능을 극대화하기 위한 효과적인 컨텍스트 엔지니어링 전략&lt;/h1>
&lt;p>&lt;strong>&lt;a href="https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents">Effective context engineering for AI agents (Anthropic, 2025-09-29)&lt;/a>&lt;/strong>&lt;/p>
&lt;h1 id="0-context란">0/ Context란?&lt;/h1>
&lt;p>Context는 LLM에서 샘플링(sampling)할 때 포함되는 토큰(token) 집합 전체를 의미한다. 여기에는 system prompt, message history, examples, tool outputs, 외부 데이터까지 포함된다. Context engineering(컨텍스트 엔지니어링)은 원하는 결과를 일관되게 얻기 위해 이러한 전체 토큰의 유용성을 최적화하는 것이다.&lt;/p></description></item><item><title>🔬 Deep Researcher with Test-Time Diffusion (Google Cloud;2025) 논문 리뷰</title><link>https://blog.watchstep.site/posts/paper_ttd-dr/</link><pubDate>Fri, 22 Aug 2025 10:49:00 +0900</pubDate><guid>https://blog.watchstep.site/posts/paper_ttd-dr/</guid><description>인간의 연구 과정에서 영감을 받아 Diffusion 방식으로 발전한 AI Deep Research Agent</description></item></channel></rss>