As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision. Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework. At each trigger point, AgentSwing expands multiple context-managed branches in parallel and uses lookahead routing to select the most promising continuation. Experiments across diverse benchmarks and agent backbones show that AgentSwing consistently outperforms strong static context management methods, often matching or exceeding their performance with up to $3\times$ fewer interaction turns while also improving the ultimate performance ceiling of long-horizon web agents. Beyond the empirical gains, the proposed probabilistic framework provides a principled lens for analyzing and designing future context management strategies for long-horizon agents.
Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
University of Arizona（亚利桑那大学）；University of Pittsburgh（匹兹堡大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Central Florida（佛罗里达中央大学）
RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm
Technical University of Denmark（技术大学）；University of Exeter（埃克塞特大学）；University of Toronto（多伦多大学）；Rutgers University（罗格斯大学）；NJIT（新 jersey 工业技术学院）；University of Georgia（佐治亚大学）；Wake Forest University（威克森林大学）
Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；College of Software Engineering, Southeast University（东南大学软件学院）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学系）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
EffGen: Enabling Small Language Models as Capable Autonomous Agents
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工大学计算机科学系）；Georgia Institute of Technology, Atlanta, GA, USA（佐治亚理工学院）；Google DeepMind, USA（谷歌DeepMind）
Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-Science
NOVA School of Science and Technology - Universidade NOVA de Lisboa（新里斯本大学新文理学院）；CIUHCT - Interuniversity Centre for the History of Science and Technology（校际科学技术史研究中心（CIUHCT））；MARE - Marine and Environmental Sciences Centre（海洋与环境科学中心（MARE））；ARNET - Aquatic Research Network Associate Laboratory（水生研究网络联合实验室（ARNET））
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
College of Design and Innovation, Tongji University（同济大学设计创意学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海自主智能无人系统科学中心）
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
Fudan University（复旦大学）；Alibaba Group（阿里巴巴集团）；The University of Hong Kong（香港大学）；Shenzhen MSU-BIT University（深圳MSU-BIT大学）；New York University（纽约大学）；Universiti Malaya（马来亚大学）；SpaceAIC Co., Ltd.（SpaceAIC公司）
Dynamic Analysis and Adaptive Discriminator for Fake News Detection
Great Bay University（大湾区大学）；Tianjin University（天津大学）；The Hong Kong Polytechnic University（香港理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beihang University（北京航空航天大学）；Sun Yat-sen University（中山大学）
