ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards

• URL: http://arxiv.org/abs/2604.20486v1
• Date: Wed, 22 Apr 2026 12:20:46 GMT
• Title: ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
• Abstract summary: ProMMSearchAgent establishes a novel Sim-to-Real training paradigm for multimodal search.<n>We generate dense behavioral metadata that explicitly rewards the correct cognitive decision.<n>ProMMSearchAgent achieves new SOTA performance, outperforming MMSearch-R1 by +5.1% on FVQA-test, +6.3% on InfoSeek, and +11.3% on MMSearch.
• Score: 24.61813749877376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and the unpredictability of live web environments. To resolve these algorithmic and environmental bottlenecks, we introduce ProMMSearchAgent, establishing a novel Sim-to-Real training paradigm for multimodal search. We decouple policy learning into a deterministic, local static sandbox. Crucially, to learn effectively within this constrained environment, we propose an introspective process-oriented reward. By probing the agent's own parametric knowledge boundaries, we generate dense behavioral metadata that explicitly rewards the correct cognitive decision, initiating a multimodal or text search only when visually or factually uncertain. Extensive experiments demonstrate that our locally-trained policy transfers zero-shot to the live Google Search API. ProMMSearchAgent achieves new SOTA performance, outperforming MMSearch-R1 by +5.1% on FVQA-test, +6.3% on InfoSeek, and +11.3% on MMSearch.

Related papers

• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents [50.79529228477821]
  We introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning.<n>First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding.<n>Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction.
  arXiv  Detail & Related papers  (2026-05-06T17:50:38Z)
• Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents [20.119608534884858]
  We propose a training-free paradigm to empower Vision-Language Models with autonomous search capabilities.<n>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.
  arXiv  Detail & Related papers  (2026-03-02T03:43:31Z)
• SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation [47.42632572449279]
  We propose SearchGym, a simulation environment designed to bootstrap robust search agents.<n>SearchGym employs a rigorous generative pipeline to construct a verifiable knowledge graph and an aligned document corpus.<n>Our results validate that high-fidelity simulation serves as a scalable and highly cost-effective methodology for developing capable search agents.
  arXiv  Detail & Related papers  (2026-01-21T03:16:17Z)
• Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search [70.63903518295785]
  We introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search.<n>Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks.
  arXiv  Detail & Related papers  (2025-10-30T09:10:36Z)
• MMSearch-R1: Incentivizing LMMs to Search [49.889749277236376]
  We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables on-demand, multi-turn search in real-world Internet environments.<n>Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty.
  arXiv  Detail & Related papers  (2025-06-25T17:59:42Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning [78.42927884000673]
  ExACT is an approach to combine test-time search and self-learning to build o1-like models for agentic applications.<n>We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore decision space on the fly.<n>Next, we introduce Exploratory Learning, a novel learning strategy to teach agents to search at inference time without relying on any external search algorithms.
  arXiv  Detail & Related papers  (2024-10-02T21:42:35Z)
• Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents [44.34340798542]
  Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities. We propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions.
  arXiv  Detail & Related papers  (2024-08-13T20:52:13Z)
• A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning [61.406020873047794]
  A major hurdle to real-world application arises from the development of algorithms in an episodic setting. We propose a new method, MEDAL, that trains the backward policy to match the state distribution in the provided demonstrations. Our experiments show that MEDAL matches or outperforms prior methods on three sparse-reward continuous control tasks.
  arXiv  Detail & Related papers  (2022-05-11T00:06:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.