10 papers
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Huanyao Zhang, Jiepeng Zhou, Jiaye Lin +9
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents remains constrained by limited c…
World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs
Yuanpeng He, Lijian Li, Dongming Jin +7
Requirement changes can affect connected stakeholders, constraints, components, and tests. We present World Requirement Model (WRM), which encodes this engineering context as a typ…
SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
Lang Mei, Xiaohan Yu, Chong Chen +27
Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons. However, training eff…
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Huanyao Zhang, Jiepeng Zhou, Runhao Zhao +12
Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to address knowledge-intensive…
Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification
Linyu Li, Zhi Jin, Yichi Zhang +6
Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse…
BrowseComp-: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimod…
RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis
Zhengwei Tao, Bo Li, Jialong Wu +5
Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of r…
DocDancer: Towards Agentic Document-Grounded Information Seeking
Qintong Zhang, Xinjie Lv, Jialong Wu +8
Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed…
AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
Huanyao Zhang, Jiaye Lin, Wentao Zhang +2
Multivariate time series forecasting involves predicting future values based on historical observations. However, existing approaches primarily rely on predefined single-scale patc…
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
Yang Shi, Huanqian Wang, Wulin Xie +20
Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is sign…