English
Related papers

Related papers: DR-MMSearchAgent: Deepening Reasoning in Multimoda…

200 papers

Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts severely limit their effectiveness in long-term dialogue agents. External memory systems have been proposed to improve memory…

Information Retrieval · Computer Science 2026-05-28 Tan Wang , Yunwei Dong

Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via…

Artificial Intelligence · Computer Science 2026-03-10 Hansi Zeng , Zoey Li , Yifan Gao , Chenwei Zhang , Xiaoman Pan , Tao Yang , Fengran Mo , Jiacheng Lin , Xian Li , Jingbo Shang

Graphical User Interface (GUI) Agents powered by Multimodal Large Language Models (MLLMs) show significant potential for automating tasks. However, they often struggle with long-horizon tasks, leading to frequent failures. Process Reward…

Artificial Intelligence · Computer Science 2025-10-06 Tao Xiong , Xavier Hu , Yurun Chen , Yuhang Liu , Changqiao Wu , Pengzhi Gao , Wei Liu , Jian Luan , Shengyu Zhang

Search-augmented reasoning agents interleave multi-step reasoning with external information retrieval, but uncontrolled retrieval often leads to redundant evidence, context saturation, and unstable learning. Existing approaches rely on…

Computation and Language · Computer Science 2026-02-03 Siheng Xiong , Oguzhan Gungordu , Blair Johnson , James C. Kerce , Faramarz Fekri

Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer…

Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in…

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Computation and Language · Computer Science 2025-02-27 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Bin Xu , Lei Hou , Juanzi Li

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large…

Artificial Intelligence · Computer Science 2025-10-14 Dayu Wang , Jiaye Yang , Weikang Li , Jiahui Liang , Yang Li

Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks…

Multiagent Systems · Computer Science 2026-02-03 Mingju Chen , Guibin Zhang , Heng Chang , Yuchen Guo , Shiji Zhou

Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn agent scenarios, where LLMs erroneously mimic their own previous responses as few-shot…

Artificial Intelligence · Computer Science 2026-05-19 Yang Wan , Zheng Cao , Zhenhao Zhang , Zhengwen Zeng , Shuheng Shen , Changhua Meng , Linchao Zhu

Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents. Tasks such as drug…

Artificial Intelligence · Computer Science 2025-12-15 Tim Cofala , Christian Kalfar , Jingge Xiao , Johanna Schrader , Michelle Tang , Wolfgang Nejdl

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a…

Artificial Intelligence · Computer Science 2025-06-03 Fernando Granado , Roberto Lotufo , Jayr Pereira

Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinforcement learning paradigms like Group Relative Policy Optimization (GRPO). However, existing…

Artificial Intelligence · Computer Science 2026-04-28 Jihao Gu , Qihang Ai , Yingyao Wang , Pi Bu , Jingxuan Xing , Zekun Zhu , Wei Jiang , Ziming Wang , Yingxiu Zhao , Ming-Liang Zhang , Jun Song , Yuning Jiang , Bo Zheng

In the rapidly evolving landscape of information retrieval, search engines strive to provide more personalized and relevant results to users. Query suggestion systems play a crucial role in achieving this goal by assisting users in…

Information Retrieval · Computer Science 2024-02-12 Zheng Wang , Bingzheng Gan , Wei Shi

Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic…

Large language models (LLMs) struggle in real-world clinical consultations. Single-turn consultation systems require patients to describe all symptoms at once, which often leads to unclear complaints and vague diagnoses. Traditional…

Computation and Language · Computer Science 2026-05-01 Yichun Feng , Jiawei Wang , Lu Zhou , Yikai Zheng , Zhen Lei , Yixue Li

Large language model agents often exhibit complementary strengths, making routing a promising approach for multi-agent question answering. However, existing routing methods remain limited in two important ways: they typically optimize over…

Computation and Language · Computer Science 2026-04-08 Jiatan Huang , Zheyuan Zhang , Kaiwen Shi , Yanfang Ye , Chuxu Zhang

Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre-defined or pre-compiled communication topologies, which…

Machine Learning · Computer Science 2026-05-18 Xingjian Wu , Junkai Lu , Siyu Yan , Xiangfei Qiu , Jilin Hu , Chenjuan Guo , Bin Yang

Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for…

Teaching large language models (LLMs) to use tools for solving complex problems can grant them human-like reasoning abilities. ReAct and its variants are popular frameworks for tool use in both single-agent and multi-agent systems. To…

Computation and Language · Computer Science 2025-06-17 Junzhi Chen , Juhao Liang , Benyou Wang