MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

arXiv:2508.13186 · cs.CL, cs.AI, cs.CV · Submitted 2025-08-14 · Read on arXiv

cs.CL, cs.AI, cs.CV

Submitted: 2025-08-14

Updated: 2026-08-31

Comments: EMNLP 2026. The first two authors contribute equally, 20 pages, repo at https://github.com/MMBrowseComp/MM-BrowseComp

Code: https://github.com/MMBrowseComp/MM-BrowseComp

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 29× in this paper · explained in 2 episodes
• Accuracy — 28× in this paper · explained in 1 episode
• Core — 10× in this paper · explained in 2 episodes
• Overall Accuracy — 9× in this paper
• Strict Accuracy — 9× in this paper
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Hallucination — 7× in this paper · explained in 4 episodes
• Verification — 6× in this paper · explained in 2 episodes
• AI Agents — 5× in this paper · explained in 2 episodes
• Failure Modes — 5× in this paper · explained in 3 episodes
• Perplexity — 5× in this paper · explained in 3 episodes
• Benchmarking — 4× in this paper · explained in 4 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 8 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Test-time Scaling — 3× in this paper · explained in 2 episodes
• Vision-language models — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 8 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Agentic Search — 1× in this paper
• Agentic System — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 19 episodes
• Temporal Consistency — 1× in this paper · explained in 3 episodes
• Verifiability — 1× in this paper · explained in 3 episodes

Sources

• Qwen2.5-VL Technical Report
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• GPT-4o System Card
• MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• LLaVA-OneVision: Easy Visual Task Transfer
• SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension
• WebSailor: Navigating Super-human Reasoning for Web Agent
• GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
• Search-o1: Agentic Search-Enhanced Large Reasoning Models
• DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
• WebGPT: Browser-assisted question-answering with human feedback
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
• Measuring short-form factuality in large language models
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering