https://botingwang.pages.dev Research notes on AI agent organization, agent self-evolution, evals, and project-grounded AI engineering. en-us Thu, 25 Jun 2026 21:36:11 GMT https://botingwang.pages.dev/articles/when-agents-learn-from-work-the-data-wall-changes/ https://botingwang.pages.dev/articles/when-agents-learn-from-work-the-data-wall-changes/ Tue, 23 Jun 2026 00:00:00 GMT Exhausting high-quality human text would not exhaust data for improving LLMs: agent work can produce new grounded experience, and selected experience can already improve later systems. https://botingwang.pages.dev/articles/why-evals-are-the-bottleneck-for-useful-agent-systems/ https://botingwang.pages.dev/articles/why-evals-are-the-bottleneck-for-useful-agent-systems/ Thu, 11 Jun 2026 00:00:00 GMT A project-grounded argument for why useful agent systems need eval infrastructure before they need more orchestration complexity.