# OmniHarness：用符号策略学习实现可泛化视觉生成

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-13 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.news/items/cmu4cwao20ipsro4wqib2ho9n
- 原文链接：https://arxiv.org/abs/2609.16057

## AI 摘要

OmniHarness 通过符号策略学习实现可泛化视觉生成，将已验证的执行抽象为符号策略，并在执行中即时验证以支持纠错与失败恢复。在 ComfyBench 的 Creative 任务上，其解决率达 95.0%，超出最强基线 27.5 个百分点。实验覆盖六个基准、三个 MLLM 主干和三个视觉智能体框架，冻结的策略快照可即插即用提升现有视觉智能体系统。

## 正文

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. (2) Reflection is often deferred until task completion. (3) Knowledge is often acquired only in response to downstream task demands. To address these limitations, we introduce OmniHarness, a framework for generalizable visual generation via symbolic policy learning. OmniHarness abstracts verified executions into symbolic policies for visual generation task families, capturing shared procedures and applicability conditions while removing instance-specific inputs.

The harness instantiates, adapts, and composes these policies for new tasks. Intermediate verification guides refinement and failure recovery during execution. Through self-directed inquiry, OmniHarness autonomously generates and executes practice tasks near its capability limits before downstream objectives are specified. Execution feedback continually refines the policies while model parameters remain fixed. Experiments across six benchmarks, three MLLM backbones, and three visual agent frameworks demonstrate strong performance and continual capability expansion.

On ComfyBench's Creative tasks, OmniHarness 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.