Metraipolis › archive › dc_c9cec235e8a4

GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms — arXiv:2608.16733

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16733
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:30.945Z
SHA-256 of the archived text
f5f77a306cbdb77026472f81026e9bfd5d727b4be8332a54fa6acc7e4ee1029e
Stable URL of this page
https://metraipolis.com/documento/dc_c9cec235e8a4

How to cite

GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms — arXiv:2608.16733 — arXiv (en), https://arxiv.org/abs/2608.16733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9cec235e8a4 (Metraipolis archive dc_c9cec235e8a4, sha256 f5f77a306cbdb77026472f81026e9bfd5d727b4be8332a54fa6acc7e4ee1029e)
BibTeX
@misc{dcc9cec235e8a4,
  title = {GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms — arXiv:2608.16733},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16733},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9cec235e8a4; sha256 f5f77a306cbdb77026472f81026e9bfd5d727b4be8332a54fa6acc7e4ee1029e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream degradation. Existing program-evolution frameworks often rely on stage-local objectives or undifferentiated multi-metric feedback, which neither guarantee better final results nor identify which unmet requirement should guide the next iteration. We present GoalEvolve, a goal-driven framework that makes physical design algorithm evolution accountable for the final quality of results (QoR) of the complete flow. Given a multi-objective QoR target region, GoalEvolve converts unmet requirements into normalized target gaps, identifies the dominant bottleneck, and uses stage-resolved checkpoint evidence to locate the responsible stage. An LLM-based Teacher then narrows the search to a relevant algorithmic decision and source region, while parallel Student agents implement and validate hypotheses through full-flow evaluation. Local effects, optimization debt, and downstream retention are retained as mechanism evidence for subsequent evolution. Across eight ASAP7 designs, GoalEvolve improves post-route TNS by 30.67% on average and reduces leakage and dynamic power by 21.18% and 9.42% versus default OpenROAD. Relative to commercial-tool goals, it closes 62.20% of the normalized power gap on power-dominant designs, surpasses the TNS goals on both timing-dominant designs, and closes 32.48% of the equal-weight timing-power gap on joint designs. Across all three designs evaluated against Codex goal mode under matched budgets, GoalEvolve further improves TNS by 26.46% while reducing leakage and dynamic power by 12.38% and 0.76%, respectively.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16733 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:14.145Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).