School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学)
Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing methods typically rely on final task outcomes as feedback for experience learning, overlooking the execution process and limiting their ability to evaluate and optimize experience based on trajectory quality. To address this limitation, we propose TQG-Exp, a trajectory-quality-guided experience-based learning framework that introduces process feedback. Specifically, we introduce Trajectory Quality Loss (TQL), which jointly considers task completion and process quality to provide a learning signal beyond final task outcomes. Based on this signal, we employ paired rollouts with and without retrieved experience to guide experience optimization. Representative trajectories are selected based on their outcomes and trajectory quality to extract task-level and task-type-level experiences. Meanwhile, differences in trajectory quality between the paired groups are used to estimate the contribution of retrieved experience and update its utility. The learned utility is then combined with semantic relevance to guide subsequent experience retrieval. Experiments on ALFWorld, WebShop, and ScienceWorld with two backbone LLMs show that TQG-Exp outperforms existing experience-based methods, improving Avg.@3 over the strongest baseline by 4.50 and 8.55 percentage points on DeepSeek-V4-Flash and Qwen3.5-Flash, respectively.
Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
School of Computer Science and Engineering, Sun Yat-sen University, China(中山大学计算机科学与工程学院);Meituan, Inc., China(美团);Shenzhen Loop Area Institute, China(深圳环区研究所);Meta AI, USA(Meta AI)
Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shanghai Jiao Tong University(上海交通大学);The Hong Kong University of Science and Technology(香港科技大学);Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院)
Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学北京校区人工智能学院);Department of Data Science, City University of Hong Kong(香港城市大学数据科学系);School of Information, Renmin University of China(中国人民大学信息学院);WeChat, Tencent(微信,腾讯)
Steering Emotional Dynamics for Art Therapy: Controllable Narrative Script Generation through Hierarchically Guided LLM Agents
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Hong Kong Baptist University(香港 Baptist 大学);South China Normal University(南方中国师范大学);Hong Kong University of Science and Technology(香港科学与技术大学);National University of Singapore(新加坡国立大学);University of Science and Technology Beijing(北京科技大学)
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Ant Group(蚂蚁集团);Zhejiang University(浙江大学);Tsinghua University(清华大学);Hangzhou Dianzi University(杭州电子科技大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Xi’an Jiaotong University(西安交通大学)
A Knowledge-Guided Cross-Modal Feature Fusion Model for Local Traffic Demand Prediction
Shandong University(山东大学);Southern University of Science and Technology(南方科技大学);Northwest University(西北大学);Didi Chuxing(滴滴出行);Renmin University of China(中国人民大学);Jilin University(吉林大学)
AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation
School of Software Engineering, South China University of Technology(软件工程学院,华南理工大学);School of Future Technology, South China University of Technology(未来技术学院,华南理工大学);Shien-Ming Wu School of Intelligent Engineering, South China University of Technology(智能工程学院,华南理工大学)
Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network
Wuhan University of Technology(武汉理工大学);School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学计算机科学与人工智能学院);University of Waterloo(滑铁卢大学)
Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
Anhui University(安徽大学);The University of Sydney(悉尼大学);Peng Cheng Laboratory(鹏城实验室);Peking University(北京大学);University of Science and Technology of China(中国科学技术大学)
Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation
Monash University(墨尔本大学);Harbin Institute of Technology(哈尔滨工业大学);Institute for Clarity in Documentation(文档清晰研究所);Inria Paris-Rocquencourt(巴黎-罗quentcourt研究所);Rajiv Gandhi University(拉朱·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒尔研究实验室)
Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences(中国科学院合肥物质科学研究院智能机械研究所);University of Science and Technology of China(中国科学技术大学)
Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming
Department of Information Systems, Business Statistics and Operations Management (ISOM), Hong Kong University of Science and Technology(香港科技大学信息系统、商务统计与运营管理系(ISOM))
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉科学学院);Wuhan AI Research(武汉人工智能研究院)
Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学安全、可靠性与信任跨学科中心);University of Luxembourg(卢森堡大学)
Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer
MAPLE Lab, Westlake University(西湖大学MAPLE实验室);Zhejiang University(浙江大学);Huazhong University of Science and Technology(华中科技大学);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖大学先进技术研究所)
RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Driving
School of Information Technology, Monash University, Malaysia(墨尔本大学信息科技学院);Faculty of Information Technology, Monash University, Australia(墨尔本大学信息技术学院);TCS Research, India(印度TCS研究)