🛰️ Daily AI Frontier
‹ back to 2026-09-07

Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool

Research LLM Agents

Ranking

Overall 78
Content 95
Popularity 37

Observed public metrics from 1 member.

Merged summary

TL;DR - SMART is an ML performance-modeling library represented primarily as a DAG of natural-language design documents, with coding agents regenerating its implementation for each version. The approach suggests design specifications may be more durable than source code for fast-changing ML systems.

  • Worked examples in the design documents serve as in-context demonstrations that improve regeneration reliability.
  • A minimal recursive operator IR combines symbolic SymPy cost expressions with analytical roll-up and modulo-scheduling modes.
  • Generated implementations matched hand-audited reference models, including DeepSeek-V3 serving on a TPU pod slice, to round-off precision.
  • Human changes are made to the design documents rather than implementation code, making the system self-documenting by construction.

Sources (1)

Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool

arXiv cs.PL Samuel Kushnir, Kimia Noorbakhsh, Kavya Sreedhar, Liqun Cheng, Ming Liu, Parthasarathy Ranganathan, Mohammad Alizadeh, Fred Kjolstad, Suvinay Subramanian 2026-09-04 arXiv:2609.05364
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-22 14:25:30.449806 UTC

TL;DR - SMART is an ML performance-modeling library represented primarily as a DAG of natural-language design documents, with coding agents regenerating its implementation for each version. The approach suggests design specifications may be more durable than source code for fast-changing ML systems.

  • Worked examples in the design documents serve as in-context demonstrations that improve regeneration reliability.
  • A minimal recursive operator IR combines symbolic SymPy cost expressions with analytical roll-up and modulo-scheduling modes.
  • Generated implementations matched hand-audited reference models, including DeepSeek-V3 serving on a TPU pod slice, to round-off precision.
  • Human changes are made to the design documents rather than implementation code, making the system self-documenting by construction.
item →