paper-with-me

홈 › Papers

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

2026-03-02 · Zhixiang Wang, Jingxuan Xu, Dajun Chen, Yunfang Wu, Wei Jiang, Yong Li arxiv

Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved evidence through multi-step reasoning. While promising, existing approaches typically rely on large-scale supervised trajectories or expensive reinforcement learning (RL), leading to high training cost, instability, and a severe cold-start problem for standard VLMs. We propose a training-free paradigm to empower VLMs with autonomous search capabilities via cross-modal model merging. By fusing a text-based search agent with a base VLM, we show that multi-modal search capabilities can be effectively composed without any additional multi-modal training data. To mitigate parameter interference during cross-modal integration, we introduce Optimal Brain Merging (OBM), a saliency-aware merging algorithm that identifies task-critical parameters based on their impact on model loss using only a small set of calibration samples. Extensive experiments on search-intensive benchmarks (e.g., InfoSeek, MMSearch) reveal that: (1) Model merging secures a reasonable performance floor as a zero-shot agent, with OBM achieving superior search rates; (2) OBM significantly raises the performance ceiling as a warm-start strategy, achieving faster convergence and higher peak accuracy than standard VLM initialization.

📄 PDF Abstract BibTeX arXiv:2603.01416

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Structure-preserving Planar Simplification for Indoor Environments

2024-08-13 · Bishwash Khanal, Sanjay Rijal, Manish Awale, Vaghawan Ojha

This paper presents a novel approach for structure-preserving planar simplification of indoor scene point clouds for both simulated and real-world environments. Initially, the scene point cloud undergoes preprocessing st…

Surface Reconstruction

The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy

2026-07-29 · Zeyu Wang arxiv

Spiking neural networks (SNNs) are promoted as an energy-efficient substrate because sparse, event-driven activity replaces dense multiply-accumulates with cheap accumulates. We argue the energy dividend of sparsity is n…

iFairy: the First 2-bit Complex LLM with All Parameters in $\{\pm1, \pm i\}$

2025-08-07 · Feiyu Wang, Guoan Wang, Yihao Zhang, Shengfan Wang 외 arxiv

Quantization-Aware Training (QAT) integrates quantization into the training loop, enabling LLMs to learn robust low-bit representations, and is widely recognized as one of the most promising research directions. All curr…

Summarization is Not Dead Yet

2026-06-06 · Dongqi Liu, Chenxi Whitehouse, Zheng Zhao, Zhuchen Cao 외 arxiv

The progress of large language models (LLMs) has fueled claims that model-generated summaries rival or even surpass human-written references, raising questions about whether summarization remains an open research problem…

When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis

2026-07-17 · S. Aaron McClendon arxiv

Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge in…

Reinforcement Learning