Long-Horizon LLM Agents

LLM: Large Language Model

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

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

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
Jun 4, 2026Yasmine Omri, Ziyu Gan, Zachary Broveak +6Agent Memory LLM Agent Memory
Stanford University · Independent Researcher · MICAS, KU Leuven +1
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Jun 4, 2026Yaoqi Chen, Haibin Lai, Yuru Feng +12Agent Memory Long-Horizon LLM Agents
University of Science and Technology of China · Microsoft · University of California, San Diego +1
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Jun 4, 2026Wenbo Pan, Shujie Liu, Chin-Yew Lin +5Software Engineering Agents Agent Harness Optimization
City University of Hong Kong · Microsoft Research Asia
AdaMEM: Test-Time Adaptive Memory for Language Agents
Jun 4, 2026Yunxiang Zhang, Yiheng Li, Ali Payani +1Agent Memory Test-Time Adaptation
University of Michigan · 2Cisco Research.
Personal AI Agent for Camera Roll VQA
Jun 3, 2026Thao Nguyen, Krishna Kumar Singh, Donghyun Kim +2Visual Question Answering Long-Horizon LLM Agents
University of Wisconsin-Madison · Adobe Research · Korea University
Multi $^2$ : Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments
Jun 2, 2026Sangeun Park, Minhae KwonMulti-Agent LLM Systems Hierarchical RL
Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea.
MemTrain: Self-Supervised Context Memory Training
Jun 2, 2026Ziheng Li, Xingrun Xing, Haoqing Wang +2LLM Agent Memory Persistent Memory for Language Models
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Samsung Research, Beijing, China
WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents
Jun 1, 2026Hengrui Gu, Xiaotian Han, Kaixiong ZhouTool-Augmented Language Model Agents Tool-Using Agents
North Carolina State University · Case Western Reserve University
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Jun 1, 2026Youwei Liu, Jian Wang, Hanlin Wang +1LLM World Models LLM Agent Training
Central South University · College of Computer Science, Sichuan University · Department of Computing, The Hong Kong Polytechnic University
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
Jun 1, 2026Zhongyu He, Yuanfan Li, Fei Huang +9LLM Agent Skill Learning Long-Horizon LLM Agents
Xiamen University · Meituan · Macao Polytechnic University
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
May 31, 2026Zhuoyun Yu, Xin Xie, Wuguannan Yao +4LLM Agent Skill Learning Failure Attribution for LLM Agents
♠Zhejiang University · ♣Ant Digital Technologies, Ant Group · ♢Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph +1
CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems
May 30, 2026Yannan Wang, Longli Yang, Zhen Liu +2LLM Agent Memory Edge Computing
Beijing Jiaotong University · Visiting PhD student at WMG, University of Warwick. · The Alan Turing Institute +2
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering
May 30, 2026Qiming Shi, Zhaolu Kang, Yunfan Zhou +2Credit Assignment in RL Step-Level Credit Assignment in RL
State Key Lab of CAD&CG, Zhejiang University · School of Software and Microelectronics, Peking University · School of Software Technology, Zhejiang University
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
May 29, 2026Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3LLM Agent Skill Learning LLM Agent Skill Retrieval
East China Normal University, Shanghai, China
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
May 28, 2026Ziyan Liu, Zhezheng Hao, Yeqiu Chen +7Long-Horizon LLM Agents Memory-Augmented Language Model Agents
University of Science and Technology of China · Zhejiang University · Tencent
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
May 28, 2026Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5RL for Language Models Terminal Agents
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences
Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
May 27, 2026Bin Wu, Guanyun Zou, Bingbing Wang +2Proactive Assistance LLM Agent Memory
Beijing University of Posts and Telecommunications · Nanjing University of Aeronautics and Astronautics · Harbin Institute of Technology (Shenzhen) +1
Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning
May 27, 2026Zhenyu Cui, Xiangzhong LuoLLM Interpretability Mechanistic Interpretability
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
May 26, 2026MiniMax, :, Aili Chen +204Mixture-of-Experts Language Models Agentic RL
Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions
May 25, 2026Jeongeun Lee, Chanyoung Park, Dongha LeeMultimodal Memory Embodied AI
Yonsei University · KAIST
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
May 25, 2026Yusong Lin, Xinyuan Liang, Haiyang Wang +8Computer-Use Agent Benchmarks AI Agent Benchmarks
Beijing Institute of Technology · Huawei Technologies Co., Ltd · Peking University +1
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
May 25, 2026Yeonjun In, Wonjoong Kim, Sangwu Park +2Memorization in Language Models Persistent Memory for Language Models
KAIST
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
May 23, 2026Yuxin Zhang, Mengxue Hu, Zheng Lin +8LLM Agent Training LLM Routing
1Fudan University · 2Alibaba Group · 3The University of Hong Kong +4
DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
May 23, 2026Lirong Che, Yuzhe yang, Peiwen lin +4Agent Harness Optimization LLM Agent Self-Improvement
Tsinghua University · AgiBot
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
May 23, 2026Yuyang Hu, Hongjin Qian, Shuting Wang +5Multi-Agent Reasoning Long-Horizon LLM Agents
GSAI, Renmin University of China · Beijing Academy of Artificial Intelligence
An Interactive Paradigm for Deep Research
May 22, 2026Lin Ai, Victor S. Bursztyn, Xiang Chen +2Deep Research Agents Human-in-the-Loop AI
Department of Computer Science, Columbia University, New York, NY, USA · Adobe Research, San Jose, CA, USA
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
May 22, 2026Jian Xie, Tianhe Lin, Zilu Wang +16Deep Research Agents LLM Agent Training
The Ohio State University · Amazon AGI SF Lab
Parallel Context Compaction for Long-Horizon LLM Agent Serving
May 22, 2026Musa Cim, Burak Topcu, Chita Das +1LLM Inference Efficiency LLM Agent Workflow Optimization
The Pennsylvania State University
Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play
May 21, 2026H. C. EkneLLM Agent Evaluation AI Agent Benchmarks
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
May 21, 2026Daewon Choi, Kyunghyun Park, Woomin Song +4LLM Inference Efficiency Long-Horizon LLM Agents
1KAIST · 3Together AI · 2Amazon AGI

Jun 4, 2026J/K move · Enter open · S save

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

Yasmine Omri, Ziyu Gan, Zachary Broveak, Robin Geens+5

Stanford University · Independent Researcher · MICAS, KU Leuven+1

Agent Memory LLM Agent Memory Long-Horizon LLM Agents Agent Memory Management

Open paper AskPDF arXiv

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.