Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

• URL: http://arxiv.org/abs/2603.28651v1
• Date: Fri, 27 Mar 2026 15:58:23 GMT
• Title: Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning
• Abstract summary: ScholScan is a new benchmark for academic paper reasoning.<n>It asks models to read and cross-check entire papers like human researchers, scanning the document to identify consistency issues.<n>The benchmark comprises 1,800 carefully annotated questions drawn from nine error categories across 13 natural-science domains and 715 papers.
• Score: 16.63278420905483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on academic paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets, with reasoning grounded in relevance retrieval, which struggles to support researcher-style full-document understanding, reasoning, and verification. To bridge this gap, we propose \textbf{ScholScan}, a new benchmark for academic paper reasoning. ScholScan introduces a scan-oriented task setting that asks models to read and cross-check entire papers like human researchers, scanning the document to identify consistency issues. The benchmark comprises 1,800 carefully annotated questions drawn from nine error categories across 13 natural-science domains and 715 papers, and provides detailed annotations for evidence localization and reasoning traces, together with a unified evaluation protocol. We assessed 15 models across 24 input configurations and conducted a fine-grained analysis of MLLM capabilities for all error categories. Across the board, retrieval-augmented generation (RAG) methods yield no significant improvements, revealing systematic deficiencies of current MLLMs on scan-oriented tasks and underscoring the challenge posed by ScholScan. We expect ScholScan to be the leading and representative work of the scan-oriented task paradigm.

Related papers

• Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper [56.13177687090277]
  We present VERA-RL, a reinforcement-learning formulation for scientific error detection over academic papers.<n>We construct VERA-13K, a 12,900-sample dataset organized into 4,300 matched chains, covering 6 scientific-error categories across the research workflow and broad natural-science domains.<n>We further introduce fine-grained rewards for reasoning completeness, evidence alignment, and error precision. Training Qwen3-VL-8B with VERA-RL substantially improves verifiable reasoning, approaching flagship MLLMs such as Gemini 3 Pro and Qwen3-VL-235B-A22B on Scan.
  arXiv  Detail & Related papers  (2026-08-27T04:24:29Z)
• Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation [60.151050016855834]
  DAS is a stateful agentic framework for generating publication-oriented academic surveys.<n>Its key idea is to separate reusable paper analysis from topic-specific manuscript construction.<n>DAS achieves the highest average in all four dimensions, with an overall score of 4.34 compared with 4.03 for the strongest competitor.
  arXiv  Detail & Related papers  (2026-08-18T17:29:00Z)
• ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments [44.35044790171568]
  We propose ScholarQuest, a large-scale, taxonomy-guided benchmark for agentic academic paper search.<n>It is constructed from over 1,000 computer science topics and four representative research intents, including method-oriented, setting-anchored, comparison-based, and scope-controlled queries.<n> Benchmarking results show that agentic methods outperform single-shot retrieval baselines, yet the best-performing agent achieves only 0.314 Recall@100 and 0.355 Recall@All, indicating substantial room for improvement.
  arXiv  Detail & Related papers  (2026-06-18T13:47:20Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery [55.70879973230979]
  AutoResearchBench is a benchmark for autonomous scientific literature discovery.<n>Compared to previous benchmarks on agentic web browsing, AutoResearchBench is research-oriented.<n>Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research.
  arXiv  Detail & Related papers  (2026-04-28T06:05:17Z)
• PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR [64.22412492998754]
  We release a search corpus of 16 million biomedical paper abstracts and construct a challenging factoid QA dataset called PaperSearchQA.<n>We train search agents in this environment to outperform non-RL retrieval baselines.<n>Our data creation methods are scalable and easily extendable to other scientific domains.
  arXiv  Detail & Related papers  (2026-01-26T06:46:16Z)
• RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension [65.81339691942757]
  RPC-Bench is a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers.<n>We design a fine-grained taxonomy aligned with the scientific research flow to assess models' ability to understand and answer why, what, and how questions in scholarly contexts.
  arXiv  Detail & Related papers  (2026-01-14T11:37:00Z)
• ELAIPBench: A Benchmark for Expert-Level Artificial Intelligence Paper Understanding [49.67493845115009]
  ELAIPBench is a benchmark curated by domain experts to evaluate large language models' comprehension of AI research papers.<n>It spans three difficulty levels and emphasizes non-trivial reasoning rather than shallow retrieval.<n>Experiments show that the best-performing LLM achieves an accuracy of only 39.95%, far below human performance.
  arXiv  Detail & Related papers  (2025-10-12T11:11:20Z)
• Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper [64.50822834679101]
  SciIG is a task that evaluates LLMs' ability to produce coherent introductions from titles, abstracts, and related works.<n>We assess five state-of-the-art models, including open-source (DeepSeek-v3, Gemma-3-12B, LLaMA 4-Maverick, MistralAI Small 3.1) and closed-source GPT-4o systems.<n>Results demonstrate LLaMA-4 Maverick's superior performance on most metrics, particularly in semantic similarity and faithfulness.
  arXiv  Detail & Related papers  (2025-08-19T21:11:11Z)
• Structured Attention Matters to Multimodal LLMs in Document Understanding [52.37530640460363]
  We investigate how input format influences document comprehension performance.<n>We discover that raw OCR text often impairs rather than improves MLLMs' performance.<n>We propose a novel structure-preserving approach that encodes document elements using the LaTex paradigm.
  arXiv  Detail & Related papers  (2025-06-19T07:16:18Z)
• SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation [2.985620880452744]
  SciSage is a multi-agent framework employing a reflect-when-you-write paradigm.<n>It critically evaluates drafts at outline, section, and document levels, collaborating with specialized agents for query interpretation, content retrieval, and refinement.<n>We also release SurveyScope, a benchmark of 46 high-impact papers ( 2020-2025) across 11 computer science domains.
  arXiv  Detail & Related papers  (2025-06-15T02:23:47Z)
• RelevAI-Reviewer: A Benchmark on AI Reviewers for Survey Paper Relevance [0.8089605035945486]
  We propose RelevAI-Reviewer, an automatic system that conceptualizes the task of survey paper review as a classification problem. We introduce a novel dataset comprised of 25,164 instances. Each instance contains one prompt and four candidate papers, each varying in relevance to the prompt. We develop a machine learning (ML) model capable of determining the relevance of each paper and identifying the most pertinent one.
  arXiv  Detail & Related papers  (2024-06-13T06:42:32Z)
• ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents [30.603079363363634]
  This study introduces ResearchArena, a benchmark designed to evaluate large language models' capabilities in conducting academic surveys.<n>ResearchArena models the process in three stages: (1) information discovery, identifying relevant literature; (2) information selection, evaluating papers' relevance and impact; and (3) information organization.<n>To support these evaluations, we construct an offline environment of 12M full-text academic papers and 7.9K survey papers.
  arXiv  Detail & Related papers  (2024-06-13T03:26:30Z)
• System for systematic literature review using multiple AI agents: Concept and an empirical evaluation [3.453564255183234]
  Systematic literature review ( SLR) is foundational to evidence-based research.<n>We introduce a novel multi-AI-agent system designed to fully automate SLRs.<n>We show how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
  arXiv  Detail & Related papers  (2024-03-13T10:27:52Z)

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.