Agents
An annotated collection of 3 papers on agents, spanning 2025 to 2026. Featuring works by Yubin Kim, Dat Tran & Douwe Kiela, Jiacheng Liu — each with editorial commentary oriented to digital product practice.
Towards a Science of Scaling Agent Systems
The first quantitative scaling principles for multi-agent AI systems, derived from 260 configurations across six benchmarks. Three findings matter: independent agent swarms can amplify baseline errors up to 17 times; too…
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
The paper that forced the multi-agent debate to control for what it should have controlled from the start: computational budget. Tran and Kiela gave single and multi-agent LLM systems identical reasoning token budgets an…
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
A systematic decomposition of how Claude Code's architecture encodes design values into implementation. The paper reverse-engineers the TypeScript source to identify five core values — safety, user agency, extensibility,…