Metraipolis › archive › dc_f43cbfe465e3
VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation — arXiv:2610.39158
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39158
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:41:49.783Z
- SHA-256 of the archived text
acacad0032afacba1b0256fb33f040901b072a18ed7d69437d0342125c03be8d- Stable URL of this page
https://metraipolis.com/documento/dc_f43cbfe465e3
How to cite
VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation — arXiv:2610.39158 — arXiv (en), https://arxiv.org/abs/2610.39158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f43cbfe465e3 (Metraipolis archive dc_f43cbfe465e3, sha256 acacad0032afacba1b0256fb33f040901b072a18ed7d69437d0342125c03be8d)
BibTeX
@misc{dcf43cbfe465e3,
title = {VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation — arXiv:2610.39158},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39158},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f43cbfe465e3; sha256 acacad0032afacba1b0256fb33f040901b072a18ed7d69437d0342125c03be8d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The central bottleneck in visual generation and editing has migrated from achieving pixel-level fidelity to satisfying densely constrained user specifications through increasingly agentic workflows. Prevailing agentic generation pipelines remain shallow generate-verify-rewrite loops treating VLM judgments as coarse visual feedback, either discarding repair experience or admitting ungated updates that poison skill library. With memorize and govern periods left open, they degrade into ungoverned iterators of repeated trial-and-error rather than continual self-evolving harness. Towards this issue, we present \textbf{VEvo-Harness}, the first causally-guarded continual self-evolving harness system for agentic visual generation. VEvo-Harness introduces four coupled innovations: (1) \textit{a visual traceback} that densifies sparse judgments into root-cause attributions with a hierarchical verification tree; (2) \textit{a visual continual governance} that admits only causally valid skill patches through counterfactual dual-arm image generation replay; (3) \textit{a lifecycle-managed harness state} that hierarchically distills root-cause-anchored episodes across working, experience, and pattern tiers into a persistent skill library of routable and causally verified capabilities; (4) \textit{a heterogeneous sandbox policy} that orchestrates a diverse action space of repair primitives, dynamically routing cost-aware interventions based on root causes to select the most effective strategy. VEvo-Harness surpasses state-of-the-art agentic methods and rivals proprietary generators (\textit{e.g.}, GPT-Image, Nano-Pro) while maintaining the continual harness evolution and generalization.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.39158 — 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 2026-11-01T02:16:43.909Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).