Metraipolis › archive › dc_96bea3427780
DFT-Agent Bench: Scaffold Effects and Execution Provenance in Autonomous DFT — arXiv:2611.10629
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10629
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:06.586Z
- SHA-256 of the archived text
acc79f04a995a4116eefada85853eeb378695ea72284287f9d1dd23ce1e8c7c0- Stable URL of this page
https://metraipolis.com/documento/dc_96bea3427780
How to cite
DFT-Agent Bench: Scaffold Effects and Execution Provenance in Autonomous DFT — arXiv:2611.10629 — arXiv (en), https://arxiv.org/abs/2611.10629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96bea3427780 (Metraipolis archive dc_96bea3427780, sha256 acc79f04a995a4116eefada85853eeb378695ea72284287f9d1dd23ce1e8c7c0)
BibTeX
@misc{dc96bea3427780,
title = {DFT-Agent Bench: Scaffold Effects and Execution Provenance in Autonomous DFT — arXiv:2611.10629},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10629},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96bea3427780; sha256 acc79f04a995a4116eefada85853eeb378695ea72284287f9d1dd23ce1e8c7c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are increasingly deployed as autonomous agents for first-principles materials simulation. We report empirical findings from DFT-Agent Bench, a benchmark of 200+ Quantum ESPRESSO tasks spanning relaxation, electronic structure, equation-of-state, and elastic-tensor pipelines over multiple material tiers. Each task carries a QE-derived ground truth with public-reference cross-checks where available, and a provenance audit checks whether the required QE execution contract was met. Under one execution harness, we compare a near-bare ReAct baseline with a bundled v5.1 scaffold on two models. The complete scaffold improves bands+DOS by +0.08/+0.11 and d-electron vc-relax by +0.17 on both models, while high-scoring relaxation and equation-of-state cells leave little room for improvement. The elastic result is model-dependent (0.18 to 0.40 for deepseek-v4-pro and 0.62 to 0.59 for claude-opus-4-8). A fixed 100-task analysis with retrieval disabled supports the aggregate pattern: the fully frozen DeepSeek comparison gains +0.17, while the Opus comparison gains +0.10 against a historical pool baseline (p < 0.001). The provenance gate catches incomplete or unmarked executions that can receive high rubric scores; it is an execution-contract check, not a test for intentional fraud. These results characterize the evaluated DFT workflows. The anonymous review artifact contains the frozen diagnostic slice, prompts, scorer, and solver revisions: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Materials Science (cond-mat.mtrl-sci). Pagina del lavoro: https://arxiv.org/abs/2611.10629 — 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 2026-11-10T18:37:37.497Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).