English
Related papers

Related papers: IterResearch: Rethinking Long-Horizon Agents with …

200 papers

The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history…

Artificial Intelligence · Computer Science 2026-05-11 Shizuo Tian , Hao Wen , Yuxuan Chen , Jiacheng Liu , Shanhui Zhao , Guohong Liu , Ju Ren , Yunxin Liu , Yuanchun Li

Large language models are transitioning from generalpurpose knowledge engines to realworld problem solvers, yet optimizing them for deep search tasks remains challenging. The central bottleneck lies in the extreme sparsity of highquality…

Artificial Intelligence · Computer Science 2026-02-17 Zheng Chu , Xiao Wang , Jack Hong , Huiming Fan , Yuqi Huang , Yue Yang , Guohai Xu , Chenxiao Zhao , Cheng Xiang , Shengchao Hu , Dongdong Kuang , Ming Liu , Bing Qin , Xing Yu

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Artificial Intelligence · Computer Science 2025-04-02 Seyoung Song

Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval, reasoning, and generation. Yet most frameworks rely on…

Computation and Language · Computer Science 2026-05-26 Lin Ai , Victor S. Bursztyn , Xiang Chen , Julia Hirschberg , Saayan Mitra

Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…

Computation and Language · Computer Science 2023-10-10 Howard Chen , Ramakanth Pasunuru , Jason Weston , Asli Celikyilmaz

Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Chenlong Deng , Mengjie Deng , Junjie Wu , Dun Zeng , Teng Wang , Qingsong Xie , Jiadeng Huang , Shengjie Ma , Changwang Zhang , Zhaoxiang Wang , Jun Wang , Yutao Zhu , Zhicheng Dou

Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histories grow. This degradation, known as context rot, reflects a…

Artificial Intelligence · Computer Science 2026-01-21 Yilun Yao , Shan Huang , Elsie Dai , Zhewen Tan , Zhenyu Duan , Shousheng Jia , Yanbing Jiang , Tong Yang

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…

Computation and Language · Computer Science 2026-05-12 Baibei Ji , Xiaoyang Weng , Juntao Li , Zecheng Tang , Yihang Lou , Min Zhang

Long-form deep research requires multi-faceted investigations over extended horizons to get a comprehensive report. When handling such complex tasks, existing agents manage context at the subtask level to overcome linear context…

Computation and Language · Computer Science 2026-01-27 Yilong Xu , Zhi Zheng , Xiang Long , Yujun Cai , Yiwei Wang

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether…

Artificial Intelligence · Computer Science 2026-05-26 Yuyang Hu , Hongjin Qian , Shuting Wang , Jiongnan Liu , Tong Zhao , Xiaoxi Li , Zheng Liu , Zhicheng Dou

Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of…

Artificial Intelligence · Computer Science 2026-04-06 Ka Yiu Lee , Yuxuan Huang , Zhiyuan He , Huichi Zhou , Weilin Luo , Kun Shao , Meng Fang , Jun Wang

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

Processing long contexts has become a critical capability for modern large language models (LLMs). Existing works leverage agent-based divide-and-conquer methods for processing long contexts. But these methods face crucial limitations,…

Computation and Language · Computer Science 2025-09-30 Sibo Xiao , Zixin Lin , Wenyang Gao , Hui Chen , Yue Zhang

Following the pivotal success of learning strategies to win at tasks, solely by interacting with an environment without any supervision, agents have gained the ability to make sequential decisions in complex MDPs. Yet, reinforcement…

Machine Learning · Computer Science 2026-03-18 Ezgi Korkmaz

With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their failure to learn from the accumulated interaction history,…

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing…

Artificial Intelligence · Computer Science 2026-05-06 Hongbo Jin , Rongpeng Zhu , Jiayu Ding , Guibo Luo , Ge Li

Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Yuhao Dong , Zuyan Liu , Hai-Long Sun , Jingkang Yang , Winston Hu , Yongming Rao , Ziwei Liu

Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but…

Artificial Intelligence · Computer Science 2026-05-26 Yuyang Hu , Hongjin Qian , Shuting Wang , Jiongnan Liu , Ziliang Zhao , Jiejun Tan , Zheng Liu , Zhicheng Dou

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Artificial Intelligence · Computer Science 2025-07-16 Junde Wu , Jiayuan Zhu , Yuyuan Liu , Min Xu , Yueming Jin

Large language model-based agents operating in long-horizon interactions require memory systems that support temporal consistency, multi-hop reasoning, and evidence-grounded reuse across sessions. Existing approaches largely rely on…

Computation and Language · Computer Science 2026-01-27 Juexiang Ye , Xue Li , Xinyu Yang , Chengkai Huang , Lanshun Nie , Lina Yao , Dechen Zhan