arxiv:2609.16057
Published on Sep 13
· Submitted by
Jinxiu on Sep 16
Upvote
3
Authors:
Xu Xu ,
,
,
,
,
,
,
Abstract
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.
View arXiv page View PDF GitHub 31 Add to collection
Community
Paper submitter 6 days ago
OmniHarness enables generalizable visual generation through symbolic policy learning, feedback-guided execution, and self-directed inquiry. The harness coordinates visual agents using a Codex reasoning backend and ComfyUI. Execution feedback refines the policy library while model parameters remain fixed.
6 days ago
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
-
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations (2026)
-
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents (2026)
-
AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models (2026)
-
Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning (2026)
-
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation (2026)
-
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on HF Mirror checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
· Sign up or log in to comment
Upvote
3
Get this paper in your agent:
hf papers read 2609.16057
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2609.16057 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.16057 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2609.16057 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.