OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
OmniHarness learns symbolic policies for visual generation agents, reaching a 95.0% resolve rate on ComfyBench Creative tasks, 27.5 points above the strongest baseline.
OmniHarness abstracts verified executions into symbolic policies for visual generation task families, which are instantiated, adapted, and composed for new tasks while model parameters remain fixed. Intermediate verification guides refinement and failure recovery during execution, and self-directed inquiry generates practice tasks near capability limits before downstream objectives are specified. Experiments across six benchmarks, three MLLM backbones, and three visual agent frameworks show strong performance; on ComfyBench Creative tasks it achieves a 95.0% resolve rate, exceeding the strongest baseline by 27.5 percentage points. Frozen policy snapshots improve existing visual agent systems through plug-and-play reuse.
- Symbolic policies capture shared procedures and applicability conditions across task families
- Model parameters stay frozen; learning happens via policy refinement
- Self-directed inquiry generates practice tasks before objectives are set
- Validated across six benchmarks and three MLLM backbones
- Products
- OmniHarnessComfyBench
- AI models
- OmniHarness
From the original article
1 min read at huggingface.co
Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability.
By Xu Xu, Jinxiu Liu, Zhangbo Qiao · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.