TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text--Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation.

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents. We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through LLM-assisted expert review. From these annotations, we build TELBench, a 1,000-instance benchmark for identifying error spans among normal exploration, failed searches, tentative hypotheses, and harmless noise. We further propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path. Experiments across model families and auditing frameworks show that DRIFT improves span-level error localization and first-error accuracy by up to 30 percentage points. Our work provides a process-level view of reliability in deep-research agents.

DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation

Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and ambiguous task definitions. We propose DR$^{3}$-Eval, a realistic and reproducible benchmark for evaluating deep research agents on multimodal, multi-file report generation. DR$^{3}$-Eval is constructed from authentic user-provided materials and paired with a per-task static research sandbox corpus that simulates open-web complexity while remaining fully verifiable, containing supportive documents, distractors, and noise. Moreover, we introduce a multi-dimensional evaluation framework measuring Information Recall, Factual Accuracy, Citation Coverage, Instruction Following, and Depth Quality, and validate its alignment with human judgments. Experiments with our developed multi-agent system DR$^{3}$-Agent based on multiple state-of-the-art language models demonstrate that DR$^{3}$-Eval is highly challenging and reveals critical failure modes in retrieval robustness and hallucination control. Our code and data are publicly available.

SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this capability from full-length clinical skill videos. It targets rubric-grounded process-level judgment of whether interaction-driven state updates preserve procedural correctness across an entire workflow. SiMing-Bench is instantiated with SiMing-Score, a physician-annotated dataset of real clinical skill examination videos spanning cardiopulmonary resuscitation, automated external defibrillator operation, and bag-mask ventilation, each paired with a standardized step-wise rubric and dual-expert labels. Across diverse open- and closed-source MLLMs, we observe consistently weak agreement with physician judgments. Moreover, weak performance on rubric-defined intermediate steps persists even when overall procedure-level correlation appears acceptable, suggesting that coarse global assessment substantially overestimates current models' procedural judgment ability. Additional analyses with binary step judgment and step-aligned clips indicate that the bottleneck is not merely fine-grained scoring or temporal localization, but modeling how continuous interactions update procedural state over time.

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice

While Large Language Models (LLMs) excel in various general domains, they exhibit notable gaps in the highly specialized, knowledge-intensive, and legally regulated Chinese tax domain. Consequently, while tax-related benchmarks are gaining attention, many focus on isolated NLP tasks, neglecting real-world practical capabilities. To address this issue, we introduce TaxPraBen, the first dedicated benchmark for Chinese taxation practice. It combines 10 traditional application tasks, along with 3 pioneering real-world scenarios: tax risk prevention, tax inspection analysis, and tax strategy planning, sourced from 14 datasets totaling 7.3K instances. TaxPraBen features a scalable structured evaluation paradigm designed through process of "structured parsing-field alignment extraction-numerical and textual matching", enabling end-to-end tax practice assessment while being extensible to other domains. We evaluate 19 LLMs based on Bloom's taxonomy. The results indicate significant performance disparities: all closed-source large-parameter LLMs excel, and Chinese LLMs like Qwen2.5 generally exceed multilingual LLMs, while the YaYi2 LLM, fine-tuned with some tax data, shows only limited improvement. TaxPraBen serves as a vital resource for advancing evaluations of LLMs in practical applications.

Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images

Recent advances in vision-language models (VLMs) have improved image captioning for cultural heritage. However, inferring structured cultural metadata (e.g., creator, origin, period) from visual input remains underexplored. We introduce a multi-category, cross-cultural benchmark for this task and evaluate VLMs using an LLM-as-Judge framework that measures semantic alignment with reference annotations. To assess cultural reasoning, we report exact-match, partial-match, and attribute-level accuracy across cultural regions. Results show that models capture fragmented signals and exhibit substantial performance variation across cultures and metadata types, leading to inconsistent and weakly grounded predictions. These findings highlight the limitations of current VLMs in structured cultural metadata inference beyond visual perception.

Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals

Online platforms increasingly rely on opinion aggregation to allocate real-world attention and resources, yet common signals such as engagement votes or capital-weighted commitments are easy to amplify and often track visibility rather than reliability. This makes collective judgments brittle under weak truth signals, noisy or delayed feedback, early popularity surges, and strategic manipulation. We propose Credibility Governance (CG), a mechanism that reallocates influence by learning which agents and viewpoints consistently track evolving public evidence. CG maintains dynamic credibility scores for both agents and opinions, updates opinion influence via credibility-weighted endorsements, and updates agent credibility based on the long-run performance of the opinions they support, rewarding early and persistent alignment with emerging evidence while filtering short-lived noise. We evaluate CG in POLIS, a socio-physical simulation environment that models coupled belief dynamics and downstream feedback under uncertainty. Across settings with initial majority misalignment, observation noise and contamination, and misinformation shocks, CG outperforms vote-based, stake-weighted, and no-governance baselines, yielding faster recovery to the true state, reduced lock-in and path dependence, and improved robustness under adversarial pressure. Our implementation and experimental scripts are publicly available at https://github.com/Wanying-He/Credibility_Governance.

EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records

Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limiting their practical relevance. To overcome this limitation, we introduce EHRNavigator, a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data. We assessed its performance using both public benchmark and institutional datasets under realistic hospital conditions characterized by diverse schemas, temporal reasoning demands, and multimodal evidence integration. Through quantitative evaluation and clinician-validated chart review, EHRNavigator demonstrated strong generalization, achieving 86% accuracy on real-world cases while maintaining clinically acceptable response times. Overall, these findings confirm that EHRNavigator effectively bridges the gap between benchmark evaluation and clinical deployment, offering a robust, adaptive, and efficient solution for real-world EHR question answering.

RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection

Cross-domain misinformation detection is challenging, as misinformation arises across domains with substantial differences in knowledge and discourse. Existing methods often rely on single-perspective cues and struggle to generalize to challenging or underrepresented domains, while reasoning large language models (LLMs), though effective on complex tasks, are limited to same-distribution data. To address these gaps, we introduce RAAR, the first retrieval-augmented agentic reasoning framework for cross-domain misinformation detection. To enable cross-domain transfer beyond same-distribution assumptions, RAAR retrieves multi-perspective source-domain evidence aligned with each target sample's semantics, sentiment, and writing style. To overcome single-perspective modeling and missing systematic reasoning, RAAR constructs verifiable multi-step reasoning paths through specialized multi-agent collaboration, where perspective-specific agents produce complementary analyses and a summary agent integrates them under verifier guidance. RAAR further applies supervised fine-tuning and reinforcement learning to train a single multi-task verifier to enhance verification and reasoning capabilities. Based on RAAR, we trained the RAAR-8b and RAAR-14b models. Evaluation on three cross-domain misinformation detection tasks shows that RAAR substantially enhances the capabilities of the base models and outperforms other cross-domain methods, advanced LLMs, and LLM-based adaptation approaches. The project will be released at https://github.com/lzw108/RAAR.

MisSpans: Fine-Grained False Span Identification in Cross-Domain Fake News

Online misinformation is increasingly pervasive, yet most existing benchmarks and methods evaluate veracity at the level of whole claims or paragraphs using coarse binary labels, obscuring how true and false details often co-exist within single sentences. These simplifications also limit interpretability: global explanations cannot identify which specific segments are misleading or differentiate how a detail is false (e.g., distorted vs. fabricated). To address these gaps, we introduce MisSpans, the first multi-domain, human-annotated benchmark for span-level misinformation detection and analysis, consisting of paired real and fake news stories. MisSpans defines three complementary tasks: MisSpansIdentity for pinpointing false spans within sentences, MisSpansType for categorising false spans by misinformation type, and MisSpansExplanation for providing rationales grounded in identified spans. Together, these tasks enable fine-grained localisation, nuanced characterisation beyond true/false and actionable explanations. Expert annotators were guided by standardised guidelines and consistency checks, leading to high inter-annotator agreement. We evaluate 15 representative LLMs, including reasoning-enhanced and non-reasoning variants, under zero-shot and one-shot settings. Results reveal the challenging nature of fine-grained misinformation identification and analysis, and highlight the need for a deeper understanding of how performance may be influenced by multiple interacting factors, including model size and reasoning capabilities, along with domain-specific textual features. This project will be available at https://github.com/lzw108/MisSpans.