Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer, they are often constrained by predefined, discrete class systems, limiting their adaptability to novel or compositional task variations. We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning via a text-conditioned Variational Autoencoder (VAE). Our core innovation utilizes a Large Language Model (LLM) as a dynamic \textit{semantic operator} at test time. Rather than relying on rigid rules, our agent queries the LLM to semantically remap the description of the current observation to align with the source task. This source-aligned caption conditions the VAE to generate an imagined state compatible with the agent's original training, enabling direct policy reuse. By harnessing the flexible reasoning capabilities of LLMs, our approach achieves zero-shot transfer across a broad spectrum of complex and truly novel analogous tasks, moving beyond the limitations of fixed category mappings. Code and videos are available \href{https://anonymous.4open.science/r/ASPECT-85C3/}{here}.
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
The Hong Kong University of Science and Technology(香港科学与技术大学);Harbin Institute of Technology(哈尔滨工业大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Nanjing University(南京大学);The University of Hong Kong(香港大学)
From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents
Tongji University(同济大学);The University of Sydney(悉尼大学);University of Science and Technology of China(中国科学技术大学);Nankai University(南开大学);Johns Hopkins University(约翰斯·霍普金斯大学);City University of Hong Kong(香港城市大学);University of Surrey(萨里大学)
SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);ShanghaiTech University(上海科技大学);University of Sussex(Sussex大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
University of Chinese Academy of Sciences(中国科学院大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);China University of Petroleum-Beijing(中国石油大学(北京))
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
ELLIS Institute Tübingen(图宾根ELLIS研究所);MPI-IS Tübingen(图宾根MPI研究所);Mila Quebec AI Institute(魁北克AI研究所);Google(谷歌);Polytechnique Montréal(蒙特利尔高等理工学院);McGill University(麦吉尔大学);Moderne(Moderne公司);Gologic(Gologic公司);Tübingen AI Center(图宾根人工智能中心);Université de Montréal(蒙特利尔大学);ServiceNow Research(ServiceNow研究)
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机技术研究所)
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
College of Connected Computing, Vanderbilt University(范德堡大学连接计算学院);School of Computer Science, The University of Sydney(悉尼大学计算机学院);Australian Centre for Robotics, The University of Sydney(悉尼大学澳大利亚机器人中心)
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
ManXis(万熙科技(ManXis));Guangdong University of Technology(广东工业大学);South China Normal University(华南师范大学);Shanghai Jiao Tong University(上海交通大学);Duke University(杜克大学);Hokkaido University(北海道大学)
Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games
NLR Royal Netherlands Aerospace Centre(荷兰皇家航空航天中心);Data Science Center of Excellence(数据科学卓越中心);Faculty of Military Sciences(军事科学学院);Tilburg University(蒂尔堡大学)
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
University of Science and Technology of China(中国科学技术大学);Meituan(美团);Institution of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Tianjin University(天津大学)
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
Temple University(天普大学);University of Central Florida(中佛罗里达大学);Arizona State University(亚利桑那州立大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Honda Research Institute USA(本田美国研究院)
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback
Beijing University of Posts and Telecommunications(北京邮电大学);North China Electric Power University(华北电力大学);Chongqing University of Posts and Telecommunications(重庆邮电大学)