Metraipolis › archive › dc_d3caea02ee88
BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification — arXiv:2609.34785
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34785
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:10.709Z
- SHA-256 of the archived text
f3568c867988369bbd208f7a273e3ad7e85bcea3ddf1b98259047314e1f1fe1d- Stable URL of this page
https://metraipolis.com/documento/dc_d3caea02ee88
How to cite
BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification — arXiv:2609.34785 — arXiv (en), https://arxiv.org/abs/2609.34785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3caea02ee88 (Metraipolis archive dc_d3caea02ee88, sha256 f3568c867988369bbd208f7a273e3ad7e85bcea3ddf1b98259047314e1f1fe1d)
BibTeX
@misc{dcd3caea02ee88,
title = {BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification — arXiv:2609.34785},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34785},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3caea02ee88; sha256 f3568c867988369bbd208f7a273e3ad7e85bcea3ddf1b98259047314e1f1fe1d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Developing agents for hardware design and verification requires reliable correctness feedback. As a hardware specification may permit correct implementations with different latencies, matching design and reference outputs cycle by cycle can reject valid designs. To address this, we introduce BEHAVE, an agentic framework for multi-turn joint hardware design and verification through functional behavior modeling. We define Behavior IR to express task functionality as executable behavior models without prescribing implementation timing beyond the specification. The agent iteratively develops a register-transfer-level (RTL) design and a behavior model as the design's verification reference. Our evaluator, BEHAVE-Sim, checks both artifacts separately against a hidden golden behavior model using input stimuli generated by random sampling and solver-guided search. BEHAVE thus supports power, performance, and area (PPA) exploration across task-permitted latencies and microarchitectures. During training, the same evaluator provides verifiable reinforcement learning (RL) rewards from specification-behavior pairs without reference RTL. For self-improvement, the agent continually searches for high-level implementations relevant to its capability gaps, constructs and checks specification-behavior pairs, and trains on the expanded task pool. We release BEHAVE-Train and BEHAVE-Eval with 600 human-reviewed specification-behavior pairs for realistic hardware workloads. Starting from 60 seed tasks and acquiring 100 new tasks, self-improvement raises Qwen3.8-27B's RTL pass@1 on BEHAVE-Eval from 55.0% to 75.0%, reaching performance comparable to RL using a 540-task pool. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Hardware Architecture (cs.AR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.34785 — 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 2026-10-07T20:29:01.665Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).