Long-Horizon LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

60 papers in the last four weeks, up 161% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 297

All topics

StepKV: Step-Aware KV Cache Compression for LLM Agents
Aug 26, 2026Boyu Feng, Jiahong Liu, Yifan Li +7KV Caching KV-Cache Compression
The Chinese University of Hong Kong · Huawei Technologies Co., Ltd
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Aug 13, 2026Yaxin Luo, Haobin Jiang, Jialv Zou +11AI Coding Agents Agent Harness Optimization
Meituan · Huazhong University of Science and Technology · Peking University +4
EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
Aug 12, 2026Le Zhang, Ke SunTemporal IR Multimodal QA
University of Michigan, Ann Arbor
LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
Aug 12, 2026Yi Wu, Zhimin HuStrategic Reasoning Risks in Language Models Long-Horizon LLM Agents
University of Chicago · University of Wisconsin-Madison
LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation
Aug 12, 2026Zhixin Zhang, Xinke Jiang, Zhibang Yang +5LLM-Guided RL LLM Agents
School of Computer Science, Peking University, Beijing, China · National Engineering Research Center for Software Engineering, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
Aug 11, 2026Aijun Yang, Qianxue Guo, Ziyi Huang +3Agentic Search LLM Agent Memory
Shanghai Jiao Tong University
OpenLoopEvolve: A Verifiable Self-Evolution Framework for Loop Policies in Long-Horizon Complex Tasks
Aug 10, 2026Siqi Wang, Xinlin Li, Zhenglin Li +1Continual Learning for LLM Agents Long-Horizon LLM Agents
UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs
Aug 10, 2026Xuexiong Yin, Zechuan Chen, Yongsen Zheng +5Tool-Use Evaluation Tool-Augmented Language Model Agents
Sun Yat-Sen University · Nanyang Technological University · Huawei Noah’s Ark Lab
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
Aug 9, 2026Yijun Pan, Yukun Lian, Kunyu Shi +5LLM Agent Evaluation AI Agent Benchmarks
1Accio Team, Alibaba Group · 2Yale University
Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents
Aug 9, 2026Harshitha Kolukuluru, Reshma Ashok, Kirat Arora +7Deep Research Agents AI Agent Evaluation
University of Massachusetts Amherst · The University of Texas at Austin · Adobe Research
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
Aug 8, 2026Yingpeng Ma, Jianhao Yan, Bei Shi +6Interactive Storytelling AI Agent Benchmarks
NLP2CT Lab, University of Macau, Macau, China · Westlake University, Hangzhou, China · Harbin Institute of Technology, Shenzhen, China +1
Agent-MD: Selective LLM Intervention with Event-Driven Escalation for Stateful GCMC--MD Campaigns
Aug 7, 2026Yijie Wang, Zhen-Yu Yin, Zhenheng Tang +1LLM Agent Orchestration Scientific Workflow Automation
Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution
Aug 7, 2026Jiahao Zhang, Yifan Zhang, Yu HuangSoftware Engineering Software Engineering Agents
Vanderbilt University
The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
Aug 7, 2026Mingguang Chen, Licheng Wang, Bo QuLong-Horizon Planning Long-Horizon Agent Evaluation
1DeepGrounding · 2AlphaAvatar
Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Aug 6, 2026Guanghui Min, Liang Wu, Mayank Darbari +2AI Agent Evaluation Long-Horizon LLM Agents
Department of Computer Science, University of Virginia, Charlottesville, VA, USA · Nokia, Sunnyvale, CA, USA
Unified Agent: Managing Interactions across Devices
Aug 6, 2026Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei +2AI Agent Benchmarks State Tracking
University of California, San Diego San Diego, CA, USA
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Aug 6, 2026Wenhao Lin, Chenyu Yu, Xingwei Lin +6LLM World Models LLM Guardrails
Zhejiang University · Nanjing University of Posts and Telecommunications · Sun Yat-sen University
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Aug 5, 2026Xuying Ning, Dongqi Fu, Tianxin Wei +17Agent Harness Optimization Long-Horizon Agent Tasks
University of Illinois Urbana–Champaign · Meta AI
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Aug 5, 2026Boxiu Li, Zimo Wen, Yijia Fan +24LLM Agent Orchestration LLM Agent Self-Improvement
Argus Team
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Aug 4, 2026Jingsheng Zheng, Xinyuan Fang, Jintian Zhang +3LLM Agent Memory Long-Horizon Agent Evaluation
Zhejiang University · Ant Group · Independent Researcher
Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
Aug 4, 2026Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich GabaLLM-Guided RL Long-Horizon LLM Agents
Department of Mathematics, AIMS, Kigali, Rwanda · African Institute for Mathematical Sciences (AIMS), Kigali, Rwanda · African Center for Advanced Studies, Pretoria, South Africa
Qwen-CUA: Native Computer Use for (almost) Everything
Aug 3, 2026Dunjie Lu, Shuai Bai, Tianyi Bai +43Computer-Use Agent Benchmarks Computer-Use Agents
MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents
Aug 3, 2026Jiajun Dong, Yutao Hu, Fengrui Fan +3LLM Agent Memory Long-Horizon LLM Agents
Huazhong University of Science and Technology, China · Fudan University, China
Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study
Aug 3, 2026Aon Safdar, Mohamed SaadeldinAI Agents for Scientific Discovery Neural Architecture Search
University College Dublin, Ireland
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Aug 3, 2026Ziyu Ma, Hailang Huang, Shun Zou +5Long-Horizon Agent Evaluation Long-Horizon LLM Agents
DreamX Team, Alibaba Group
Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents
Aug 2, 2026Yidan Lin, Kaixiang Wang, Jiong Lou +1LLM Inference Efficiency Efficient Inference
TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
Aug 2, 2026Jingyu Sun, Yuyang Xue, Mingyang Li +9Agent Memory LLM Agent Memory
1The University of Manchester · 2The University of Melbourne · 3The University of Edinburgh +2
PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
Aug 2, 2026Jingyu Sun, Yan Lin, Yuyang Xue +10Memory-Augmented VLMs Multimodal Memory
The University of Manchester · The University of Newcastle · The University of Edinburgh +5
HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
Jul 31, 2026An Liu, Bingxi Liu, Hongyu Ding +6Memory-Augmented VLMs Vision-Language Navigation
Institute of Automation, Chinese Academy of Sciences, Beijing, China · Southern University of Science and Technology, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China +3
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
Jul 31, 2026Qiming Shi, Yulong Tao, Linbo Jin +10LLM Agent Evaluation Long-Horizon Agent Evaluation
2State Key Lab of CAD&CG, Zhejiang University · 1Alibaba Group · School of Software and Microelectronics, Peking University +2

Aug 26, 2026, cs.LGJ/K move · Enter open · S save

StepKV: Step-Aware KV Cache Compression for LLM Agents

Boyu Feng, Jiahong Liu, Yifan Li, Wenhao Yu+6

The Chinese University of Hong Kong · Huawei Technologies Co., Ltd

KV Caching KV-Cache Compression Long-Horizon LLM Agents KV-Cache Pruning

Open paper AskPDF arXiv

Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length, increasing storage and decoding costs. KV cache compression mitigates this cost by retaining only a subset of cached tokens. This challenge is particularly important for multi-step LLM agents, where a query expands into trajectories of reasoning, tool interactions, and retrieved observations. Existing pruning methods typically treat the cache as a flat token stream and rank tokens by recency or attention saliency. This creates a mismatch between the unit of compression and the unit of reasoning: token-level pruning removes individual entries, whereas useful information in multi-step agents is often organized into reasoning steps with uneven and delayed importance. Consequently, an early observation or intermediate decision may receive little recent attention yet remain essential for later evidence synthesis. We term this failure mode Reasoning Continuity Disruption.These observations motivate KV cache compression that jointly considers token- and reasoning-step-level information. StepKV addresses this goal by treating reasoning steps as first-class retention units. It associates cache entries with their generating steps, estimates step utility from trajectory-derived signals, and combines this utility with token-level saliency. The resulting scores globally rank prunable tokens, from which StepKV retains the top-scoring entries under a target budget. StepKV thus provides a step-centric perspective for agent KV cache compression. Across multi-hop QA and long-horizon web reasoning tasks, StepKV sustains accuracy under low KV budgets where token-level baselines degrade sharply, offering a more robust efficiency-accuracy trade-off for multi-step agent inference.

Momentum

Related topics

Latest papers 297