UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp

• URL: http://arxiv.org/abs/2607.10557v1
• Date: Sun, 12 Jul 2026 04:13:27 GMT
• Title: UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp
• Abstract summary: Real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image.<n>We introduce UNIBROWSE, a unified data pipeline that simultaneously generates training data covering all three patterns.<n>The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks.
• Score: 14.339105360523831
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware RL.The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks -- an improvement of 10.5 points over its base model Qwen3.5-35B-A3B -- and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).

Related papers

• WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing [51.8784267764917]
  We present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend.<n>We first introduce WeAgent-Harness, a multimodal runtime with persistent evidence management and dedicated verification and integration tools that organize retrieved multimodal evidence into a dense carrier. Upon this, we develop a scalable pipeline for prompt synthesis and agentic trajectory collection, yielding 23K supervised trajectories and 14.7K RL tasks with three-layer verifiable checklists.
  arXiv  Detail & Related papers  (2026-09-04T14:12:03Z)
• Rendering-in-the-Loop: An Execution-Driven Agent for Interactive Web Development [11.314424904357212]
  We present RILA, an execution-driven agent that puts browser rendering in the loop, iteratively editing generated code from runtime interaction feedback.<n>On IWR-Bench, RILA consistently improves both interaction and visual fidelity across foundation models.
  arXiv  Detail & Related papers  (2026-09-02T04:27:45Z)
• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation [26.8807904319691]
  We present textbfSearchEyes, which uses a typed knowledge graph as the backbone of a emphsimulated search world<n>We propose textbfPerception-Knowledge Chains (PKC) to sample constrained multi-hop paths over the visual-knowledge intersection of Wikidata5M.<n>Experiments on six multimodal knowledge-intensive benchmarks show that SearchEyes achieves state-of-the-art performance among open-source multimodal search agents.
  arXiv  Detail & Related papers  (2026-07-07T07:43:04Z)
• EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents [64.96332056338923]
  EEVEE is the first multi-dataset test-time prompt learning framework for LLM agents.<n>It enables test-time prompt learning under real-world task streams.<n>EEVEE improves average multi-benchmark scores by 10.38 and 24.32 points over Qwen3-4B-Instruct and DeepSeek-V3.2.
  arXiv  Detail & Related papers  (2026-06-09T17:57:16Z)
• MTA-Agent: An Open Recipe for Multimodal Deep Search Agents [51.180338423927985]
  Multi-hop large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning.<n>We propose a Multi-hop Tool-Augmented Agent for Evidence-based QA Synthesis (MTA-Agent)<n>MTA-Agent automatically selects tools and their parameters to retrieve and validate evidence from both visual and textual sources.
  arXiv  Detail & Related papers  (2026-04-07T19:01:45Z)
• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning [15.087327596252932]
  Existing multi-agent systems often rely on hand-crafted and turn-taking interactions that fail to parallelize work effectively.<n>We propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution.<n>Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B.
  arXiv  Detail & Related papers  (2026-02-04T15:05:12Z)
• PRInTS: Reward Modeling for Long-Horizon Information Seeking [74.14496236655911]
  We introduce PRInTS, a generative PRM trained with dual capabilities.<n>We show that PRInTS enhances information-seeking abilities of open-source models as well as specialized agents.
  arXiv  Detail & Related papers  (2025-11-24T17:09:43Z)
• A Modular, Data-Free Pipeline for Multi-Label Intention Recognition in Transportation Agentic AI Applications [12.25149118082394]
  A modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation.<n>Unlike traditional intent recognition systems that depend on large, annotated corpora, our approach eliminates the need for costly data collection.<n>Our system seamlessly routes user queries to task-specific modules, laying the groundwork for fully autonomous, intention-aware agents.
  arXiv  Detail & Related papers  (2025-11-05T11:08:08Z)
• TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments [30.078263383249862]
  Toucan is the largest publicly available tool-agentic dataset to date.<n>It generates diverse, realistic, and challenging tasks with trajectories involving real tool execution.
  arXiv  Detail & Related papers  (2025-10-01T17:58:03Z)
• mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data [71.352883755806]
  Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space.<n>However, the limited labeled multimodal data often hinders embedding performance.<n>Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck.
  arXiv  Detail & Related papers  (2025-02-12T15:03:33Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)

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.