{"slug": "symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning", "title": "SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning", "summary": "Researchers propose SymbOmni, an agentic omni-model that uses Symbolic Concept Learning to overcome the 'perpetual novice' problem in visual generation. The model outperforms existing agent-based and closed-source systems in image quality and task success while reducing token consumption by over 40%. SymbOmni achieves cumulative gains in continual learning benchmarks, setting a new state of the art.", "body_md": "arXiv:2607.12042v1 Announce Type: new\nAbstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing monolithic models remain fundamentally constrained by their inability to learn cumulatively and evolve autonomously, which is a limitation we term the \"perpetual novice\" problem. They lack mechanisms for structuring experience into reusable knowledge and therefore rely on brittle, \"from-scratch\" reasoning for each task, resulting in poor compositional generalization and inefficient knowledge retention. Motivated by these limitations, we propose SymbOmni, an agentic omni-model designed for cumulative evolution through Symbolic Concept Learning. At its core is the Symbolic Concept Box, an optimizable memory module that abstracts low-level operations into reusable Symbolic Workflow Instructions. SymbOmni operates through an induction-transduction cycle: experiences are abstracted into symbolic concepts (induction), which are then adaptively composed to solve novel tasks (transduction). The training is done by verbalized backpropagation with language-based feedback to enable continuous self-improvement without gradient-based model fine-tuning. Comprehensive experiments validate that (I) SymbOmni significantly outperforms existing agent-based systems for iterative creation and also surpasses closed-source models (e.g., Nano Banana, GPT-Image-1) in both image quality and task success rates; (II) SymbOmni effectively reduces token consumption by over 40% while maintaining competitive generation quality; and (III) SymbOmni enables effective continual learning by achieving cumulative gains across multiple online-learning benchmarks and setting a new state of the art.", "url": "https://wpnews.pro/news/symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning", "canonical_source": "https://arxiv.org/abs/2607.12042", "published_at": "2026-07-15 04:00:00+00:00", "updated_at": "2026-07-15 04:01:16.011001+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai", "ai-agents", "computer-vision"], "entities": ["SymbOmni", "Nano Banana", "GPT-Image-1"], "alternates": {"html": "https://wpnews.pro/news/symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning", "markdown": "https://wpnews.pro/news/symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning.md", "text": "https://wpnews.pro/news/symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning.txt", "jsonld": "https://wpnews.pro/news/symbomni-evolving-agentic-omni-models-via-symbolic-concept-learning.jsonld"}}