Related papers: MM-Doc-R1: Training Agents for Long Document Visua…

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Group Relative Policy…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are…

A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Augmented Generation (RAG). However, the vanilla approach that simply concatenates multiple…

Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models, thereby enhancing factuality and reducing hallucinations in question-answering (QA) tasks. A standard RAG pipeline…

Retrieval-Augmented Generation (RAG) enhances the accuracy of Large Language Model (LLM) responses by leveraging relevant external documents during generation. Although previous studies noted that retrieving many documents can degrade…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However,…

Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while…

Spatial reasoning remains a critical yet underdeveloped capability in existing vision-language models (VLMs), especially for Spatial Visual Question Answering (Spatial VQA) tasks that require understanding relative positions, distances, and…

Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new information. Retrieval-Augmented Generation (RAG) addresses…

Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This…

Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and non-learnable tool invocation mechanisms, which limit the…

Large Vision-Language Models (LVLMs) have become powerful general-purpose assistants, yet their predictions often lack reliability and interpretability due to insufficient grounding in visual evidence. The emerging thinking-with-images…

Understanding multi-page documents poses a significant challenge for multimodal large language models (MLLMs), as it requires fine-grained visual comprehension and multi-hop reasoning across pages. While prior work has explored…

Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities.…