Tag
APDMem introduces a hierarchical long-term memory architecture for LLM assistants that applies agent-controlled progressive disclosure over four memory layers, achieving strong LongMemEval performance while accessing only 8% of conversation data.
Google's blog post introduces Agent Skills support in Genkit for Go, demonstrating how progressive disclosure lets agents load specialized knowledge on demand to reduce token usage and improve reliability.
This paper presents SkillJuror, a framework for evaluating how different organizational paradigms for Agent Skills affect LLM agent runtime behavior. A study on 82 tasks shows that Progressive Disclosure increases resource diversity and uptake events compared to a flat baseline, with task-dependent outcome improvements.
Anthropic published a blog explaining the concept of Skills in Claude Code: Skills are a folder containing instructions, scripts, reference materials, etc., enabling the Agent to progressively disclose context, reducing hallucinations and token waste.
This article shares a practical guide to writing a truly usable Claude Skill, covering the operating mechanism, directory skeleton, frontmatter writing, iteration methods, etc., to help developers efficiently build and debug custom skills.
Matt Pocock asks for feedback on his proposed principles for skills: concise, single-responsibility, composable, progressively disclosed, and harness-agnostic.
A defense of MCP (Model Context Protocol) against criticism that it puts garbage in context, noting that modern tools like Claude Code, Codex, and Cursor implement progressive disclosure and load MCP tools on demand, making the complaint outdated. The author argues MCP is best for cloud-hosted platforms requiring authentication and discoverability.