As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this challenge, extracting reusable knowledge from interaction traces, yet a citation analysis of 1{,}136 references across 22 primary papers reveals a cross-community citation rate below 1\%. We propose the \emph{Experience Compression Spectrum}, a unifying framework that positions memory, skills, and rules as points along a single axis of increasing compression (5--20$\times$ for episodic memory, 50--500$\times$ for procedural skills, 1{,}000$\times$+ for declarative rules), directly reducing context consumption, retrieval latency, and compute overhead. Mapping 20+ systems onto this spectrum reveals that every system operates at a fixed, predetermined compression level: none supports adaptive cross-level compression, a gap we term the \emph{missing diagonal}. We further show that specialization alone is insufficient (both communities independently solve shared sub-problems without exchanging solutions), that evaluation methods are tightly coupled to compression levels, that transferability increases with compression at the cost of specificity, and that knowledge lifecycle management remains largely neglected. We articulate open problems and design principles for scalable, full-spectrum agent learning systems.
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Qwen Large Model Application Team, Alibaba(通义千问大模型应用团队,阿里巴巴);Sun Yat-sen University(中山大学);The Chinese University of Hong Kong(香港中文大学);Peking University(北京大学);ETH Zürich University of Zurich(苏黎世联邦理工学院)
UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Hong Kong Polytechnic University(香港理工大学);Stepfun
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
Zhejiang University(浙江大学);Carnegie Mellon University(卡内基梅隆大学);University of Chinese Academy of Sciences(中国科学院大学);University of Science and Technology of China(中国科学技术大学);Alibaba(阿里巴巴)
Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi(德里印度理工学院亚迪人工智能学院);Indian Institute of Technology Delhi(德里印度理工学院);Microsoft Research (MSR) India(微软研究院印度分部)
Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China(脑启发智能感知与认知教育部重点实验室,中国科学技术大学);Huawei Technologies Co., Ltd.(华为技术有限公司);College of Intelligence and Computing, Tianjin University(智能与计算学院,天津大学)
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
Helmholtz Munich(海德堡大学慕尼黑分校);Max Planck Institute for Biological Cybernetics(生物 cybernetics 最大计划研究所);Princeton University(普林斯顿大学);University of Tübingen(图宾根大学)
RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents
School of Geosciences and Info-Physics, Central South University(地质科学与信息物理学院,中南大学);School of Resources and Environment, University of Electronic Science and Technology of China(资源与环境学院,电子科技大学);School of Earth Sciences and Spatial Information Engineering, Hunan University of Science and Technology(地球科学与空间信息工程学院,湖南科技大学);Sanya Institute of Hunan University of Science and Technology(海南科技大学三亚研究院)
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, San Diego(加利福尼亚大学圣迭戈分校);University of California, Merced(加利福尼亚大学默塞德分校);Adobe Research(奥多比研究院);Texas A&M University(德克萨斯农工大学)
Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
Key Laboratory of Interdisciplinary Research of Computation and Economics(交叉计算与经济学交叉研究实验室);Shanghai University of Finance and Economics(上海财经大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, Chinese Academy of Sciences(中国科学院人工智能研究所);University of Bristol(布里斯托大学);Peking University(北京大学);University College London(伦敦大学学院)