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

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.

THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics

We present THEMIS, a novel multi-task benchmark designed to comprehensively evaluate multimodal large language models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advances. (1) Real-World Scenarios and Complexity: Our benchmark comprises over 4,000 questions spanning seven scenarios, derived from authentic retracted-paper cases and carefully curated multimodal synthetic data. With 60.47% complex-texture images, THEMIS bridges the critical gap between existing benchmarks and the complexity of real-world academic fraud. (2) Fraud-Type Diversity and Granularity: THEMIS systematically covers five challenging fraud types and introduces 16 fine-grained manipulation operations. On average, each sample undergoes multiple stacked manipulation operations, with the diversity and difficulty of these manipulations demanding a high level of visual fraud reasoning from the models. (3) Multi-Dimensional Capability Evaluation: We establish a mapping from fraud types to five core visual fraud reasoning capabilities, thereby enabling an evaluation that reveals the distinct strengths and specific weaknesses of different models across these core capabilities. Experiments on 16 leading MLLMs show that even the best-performing model, GPT-5, achieves an overall performance of only 56.15%, demonstrating that our benchmark presents a stringent test. We expect THEMIS to advance the development of MLLMs for complex, real-world fraud reasoning tasks.

FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation

We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to existing benchmarks, our work delivers three major advancements. (1) Scenario Awareness: 57.9% of 1,200 expert-annotated problems incorporate 12 types of implicit financial scenarios (e.g., Portfolio Management), challenging models to perform expert-level reasoning based on assumptions; (2) Document Understanding: 837 Chinese/English documents spanning 9 types (e.g., Company Research) average 50.8 pages with rich visual elements, significantly surpassing existing benchmarks in both breadth and depth of financial documents; (3) Multi-Step Computation: Problems demand 11-step reasoning on average (5.3 extraction + 5.7 calculation steps), with 65.0% requiring cross-page evidence (2.4 pages average). The best-performing MLLM achieves only 58.0% accuracy, and different retrieval-augmented generation (RAG) methods show significant performance variations on this task. We expect FinMMDocR to drive improvements in MLLMs and reasoning-enhanced methods on complex multimodal reasoning tasks in real-world scenarios.

FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging

We present FinMMR, a novel bilingual multimodal benchmark tailored to evaluate the reasoning capabilities of multimodal large language models (MLLMs) in financial numerical reasoning tasks. Compared to existing benchmarks, our work introduces three significant advancements. (1) Multimodality: We meticulously transform existing financial reasoning benchmarks, and construct novel questions from the latest Chinese financial research reports. FinMMR comprises 4.3K questions and 8.7K images spanning 14 categories, including tables, bar charts, and ownership structure charts. (2) Comprehensiveness: FinMMR encompasses 14 financial subdomains, including corporate finance, banking, and industry analysis, significantly exceeding existing benchmarks in financial domain knowledge breadth. (3) Challenge: Models are required to perform multi-step precise numerical reasoning by integrating financial knowledge with the understanding of complex financial images and text. The best-performing MLLM achieves only 53.0% accuracy on Hard problems. We believe that FinMMR will drive advancements in enhancing the reasoning capabilities of MLLMs in real-world scenarios.

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, an agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction, and optimizes the agent process via an end-to-end reward mechanism. Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality.

FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging

We introduce FinanceReasoning, a novel benchmark designed to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. Compared to existing benchmarks, our work provides three key advancements. (1) Credibility: We update 15.6% of the questions from four public datasets, annotating 908 new questions with detailed Python solutions and rigorously refining evaluation standards. This enables an accurate assessment of the reasoning improvements of LRMs. (2) Comprehensiveness: FinanceReasoning covers 67.8% of financial concepts and formulas, significantly surpassing existing datasets. Additionally, we construct 3,133 Python-formatted functions, which enhances LRMs' financial reasoning capabilities through refined knowledge (e.g., 83.2% $\rightarrow$ 91.6% for GPT-4o). (3) Challenge: Models are required to apply multiple financial formulas for precise numerical reasoning on 238 Hard problems. The best-performing model (i.e., OpenAI o1 with PoT) achieves 89.1% accuracy, yet LRMs still face challenges in numerical precision. We demonstrate that combining Reasoner and Programmer models can effectively enhance LRMs' performance (e.g., 83.2% $\rightarrow$ 87.8% for DeepSeek-R1). Our work paves the way for future research on evaluating and improving LRMs in domain-specific complex reasoning tasks.

HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation

While standard Retrieval-Augmented Generation (RAG) based on chunks, GraphRAG structures knowledge as graphs to leverage the relations among entities. However, previous GraphRAG methods are limited by binary relations: one edge in the graph only connects two entities, which cannot well model the n-ary relations among more than two entities that widely exist in reality. To address this limitation, we propose HyperGraphRAG, a novel hypergraph-based RAG method that represents n-ary relational facts via hyperedges, modeling the complicated n-ary relations in the real world. To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism. Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms standard RAG and GraphRAG in accuracy and generation quality.

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB). Despite advancements with large language models (LLMs), KBQA still faces challenges in weak KB awareness, imbalance between effectiveness and efficiency, and high reliance on annotated data. To address these challenges, we propose KBQA-o1, a novel agentic KBQA method with Monte Carlo Tree Search (MCTS). It introduces a ReAct-based agent process for stepwise logical form generation with KB environment exploration. Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space. With heuristic exploration, KBQA-o1 generates high-quality annotations for further improvement by incremental fine-tuning. Experimental results show that KBQA-o1 outperforms previous low-resource KBQA methods with limited annotated data, boosting Llama-3.1-8B model's GrailQA F1 performance to 78.5% compared to 48.5% of the previous sota method with GPT-3.5-turbo.

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

Knowledge Base Question Answering (KBQA) aims to derive answers to natural language questions over large-scale knowledge bases (KBs), which are generally divided into two research components: knowledge retrieval and semantic parsing. However, three core challenges remain, including inefficient knowledge retrieval, retrieval errors adversely affecting semantic parsing, and the complexity of previous KBQA methods. In the era of large language models (LLMs), we introduce ChatKBQA, a novel generate-then-retrieve KBQA framework built on fine-tuning open-source LLMs such as Llama-2, ChatGLM2 and Baichuan2. ChatKBQA proposes generating the logical form with fine-tuned LLMs first, then retrieving and replacing entities and relations through an unsupervised retrieval method, which improves both generation and retrieval more straightforwardly. Experimental results reveal that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and ComplexWebQuestions (CWQ). This work also provides a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering. Our code is publicly available.

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction

Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs still significantly relies on manual labor, and n-ary relation extraction still remains at a course-grained level, which is always in a single schema and fixed arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. Experimental results demonstrate that Text2NKG outperforms the previous state-of-the-art model by nearly 20\% points in the $F_1$ scores on the fine-grained n-ary relation extraction benchmark in the hyper-relational schema. Our code and datasets are publicly available.