Long-Horizon LLM Agents

LLM: Large Language Model

Ask about this topic

Overview

Long-horizon LLM agents are systems designed to pursue goals through many connected actions, often while using tools and responding to changing information. Common approaches include hierarchical planning and subgoals, reinforcement learning with step-level or milestone rewards, persistent memory and context compression, and harnesses that verify actions and recover from errors. Researchers evaluate them in interactive settings such as ALFWorld, WebShop, ScienceWorld, WebArena, software-engineering benchmarks, and deep-research tasks. A central challenge is making performance reliable over time: errors and lost constraints can compound, while memory, verification, and extra computation can improve success but add cost or introduce new failure modes.

Latest papers

CardsList

451 papers92 papers in the last four weeks, up 56% on the four weeks before. 0.5% of all new papers.

  1. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

    Mar 16, 2026MiroMind Team, S. Bai, L. Bing +41Autonomous Research AgentsLong-Horizon LLM Agents

  2. Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective

    Mar 15, 2026Mohamed Aghzal, Gregory J. Stein, Ziyu YaoWeb AgentsLLM Agent Reliability

    Department of Computer Science, George Mason University

  3. StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context

    Mar 13, 2026Sasank Annapureddy, John Mulcahy, Anjaneya Prasad ThamataniLLM Context ManagementPersistent Memory for Language Models

  4. BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning

    Mar 12, 2026Xiaoyu Ma, Lianyu Hu, Wenbing Tang +4Long-Term Memory for Embodied AgentsMemory-Augmented Language Model Agents

    Nanyang Technological University, Singapore · Tianjin University, Tianjin, China

  5. From Control to Foresight: Simulation as a New Paradigm for Human-Agent Collaboration

    Mar 12, 2026Gaole He, Brian Y. LimHuman-AI CollaborationHuman-in-the-Loop AI

    National University of Singapore, Singapore

  6. Deep Tabular Research via Continual Experience-Driven Execution

    Mar 10, 2026Junnan Dong, Chuang Zhou, Zheng Yuan +7Table QALong-Horizon LLM Agents

    Tencent Youtu Lab · Ruijin Hospital, Shanghai Jiaotong University

  7. DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation

    Mar 8, 2026Shuzhang Zhong, Baotong Lu, Qi Chen +3Deep Research AgentsLLM Inference Acceleration

    Peking University, Beijing, China · Microsoft Research · Microsoft

  8. Hindsight Credit Assignment for Long-Horizon LLM Agents

    Mar 7, 2026Hui-Ze Tan, Xiao-Wen Yang, Hao Chen +7Credit Assignment in RLLong-Horizon LLM Agents

    State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · FiT, Tencent, Shenzhen, China +2

  9. STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

    Mar 5, 2026ELita Lobo, Xu Chen, Jingjing Meng +5LLM Agent PlanningLong-Horizon LLM Agents

    University of Massachusetts Amherst · Amazon · Virginia Commonwealth University +1

  10. HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel

    Mar 5, 2026The Viet Bui, Wenjun Li, Yong LiuTravel PlanningLong-Horizon LLM Agents

    Singapore Management University

  11. Mozi: Governed Autonomy for Drug Discovery LLM Agents

    Mar 4, 2026He Cao, Siyu Liu, Fan Zhang +7AI Agents for Scientific DiscoveryLLM Agent Orchestration

  12. VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning

    Mar 3, 2026Ruiyang Zhang, Qianguo Sun, Chao Song +2Multimodal Search AgentsMultimodal Tool Use

    FST and ICI, University of Macau, China · IDEA

  13. Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI

    Mar 1, 2026Sicheng Yang, Yukai Huang, Weitong Cai +8Web AgentsTool-Using Vision-Language Agents

    Shenzhen International Graduate School Tsinghua University Shenzhen, China · Independent Researcher London, United Kingdom · Queen Mary University of London London, United Kingdom +2

  14. HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

    Mar 1, 2026Hongbo Jin, Rongpeng Zhu, Jiayu Ding +2Long-Horizon LLM AgentsLong-Horizon Agent Tasks

    School of Electronic and Computer Engineering, Peking University

  15. M2^2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval

    Feb 28, 2026Dawei Yan, Haokui Zhang, Guangda Huzhang +8Long-Horizon LLM AgentsWeb Agents

    Northwestern Polytechnical University, Xi’an, China · AI Business, Alibaba Group, Hangzhou, China · Xi’an University of Architecture and Technology, Xi’an, China +1

  16. PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents

    Feb 27, 2026Yihan, Wen, Xin ChenLLM Agent PlanningLong-Horizon LLM Agents

    Logon · Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA

  17. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

    Feb 26, 2026Zhaochen Su, Jincheng Gao, Hangyu Guo +10Multimodal Agent EvaluationAI Agent Benchmarks

    Hong Kong University of Science and Technology · University of North Carolina at Chapel Hill · Zhejiang University +1

  18. DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

    Feb 26, 2026Hao Zheng, Guozhao Mo, Xinru Yan +7Agentic AILLM Agents

    Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

  19. Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

    Feb 26, 2026Qianben Chen, Tianrui Qin, King Zhu +21Agentic SearchLong-Horizon LLM Agents

  20. Structurally Aligned Subtask-Level Memory for Software Engineering Agents

    Feb 25, 2026Kangning Shen, Jingyuan Zhang, Chenxi Sun +2LLM Agent MemoryAgent Memory

    Kuaishou Technology, Beijing, China

  21. Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

    Feb 24, 2026Yining Hong, Huang Huang, Manling Li +4Large Language Model-Based Robot PlanningLLM Agent Planning

    Stanford University · Northwestern University

  22. Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks

    Feb 22, 2026Wilson Y. LeeAgent Failure AnalysisLLM Agent Reliability

    Independent Researcher United States

  23. Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems

    Feb 20, 2026Hanjing Shi, Dominic DiFranzoLong-Horizon LLM AgentsLLM Agent Workflow Optimization

    Lehigh University, Bethlehem, Pennsylvania, USA

  24. KLong: Training LLM Agent for Extremely Long-horizon Tasks

    Feb 19, 2026Yue LiuLLM Agent TrainingLong-Horizon Agent Tasks

    NUS

  25. ResearchGym: Evaluating Language Model Agents on Real-World AI Research

    Feb 16, 2026Aniketh Garikaparthi, Manasi Patwardhan, Arman CohanAI Agent BenchmarksAutonomous Research Agents

    TCS Research · Yale University

  26. PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning

    Feb 14, 2026Yu Li, Guangfeng Cai, Shengtian Yang +5LLM-Guided RLTool-Use Planning

    School of Computer Science and Engineering, Southeast University, Nanjing, China · Huawei Noah’s Ark Lab, China

  27. Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

    Feb 11, 2026Yihang Yao, Zhepeng Cen, Haohong Lin +6Agentic RLLLM Agents

    Carnegie Mellon University · Salesforce AI Research · Massachusetts Institute of Technology +2

  28. StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

    Jan 9, 2026Ruizhe Zhang, Xinke Jiang, Zhibang Yang +12Multi-Agent LLM SystemsMulti-Agent Collaboration

    School of Computer Science, Peking University, Beijing, China · 2National Engineering Research Center for Software Engineering, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +5

  29. CaveAgent: Transforming LLMs into Stateful Runtime Operators

    Jan 4, 2026Maohao Ran, Zhenglin Wan, Cooper Lin +21LLM Agent MemoryLLM Agents

    HKUST · HKBU · NUS +8

  30. LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?

    May 17, 2025Idriss Malek, Omar Choukrani, Daniil Orel +5LLM PlanningLLM Agent Evaluation

    Tandon School of Engineering New York University · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi, UAE