AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
Zibo Shao, Baochen Xiong, Chengdong Xu, Linhui Xiao, Kaichen Li, Haoran Gong, Yan Li, Yaguang Song, Xiaoshan Yang
cs.AI, cs.CV
Submitted: 2026-08-07
Updated: 2026-08-10
Code: https://github.com/ziboshao/AgentPatch
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Model Composition for Multimodal Large Language Models
- Fusing finetuned models for better pretraining
- ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging
- WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
- Editing Models with Task Arithmetic
- MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines
- LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
- Model merging with SVD to tie the Knots
- An Empirical Study of Multimodal Model Merging
- Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
- MMSearch-R1: Incentivizing LMMs to Search
- V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection