AI Agent

SpeakStream: Streaming Text-to-Speech with Interleaved Data

Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly

机构 * Apple（苹果公司） 纠错

专题命中 记忆与上下文管理 ：AI agent(abstract)；分类 cs.CL、cs.LG

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

Ran Li, Hao Wang, Chengzhi Mao

机构 * Columbia University（哥伦比亚大学） ； Rutgers University（罗格斯大学） 纠错

专题命中 记忆与上下文管理 ：agentic(abstract)；分类 cs.CL、cs.LG

MARK: Memory Augmented Refinement of Knowledge

Anish Ganguli, Prabal Deb, Debleena Banerjee

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Modeling Behavioral Preferences of Cyber Adversaries Using Inverse Reinforcement Learning

Aditya Shinde, Prashant Doshi

机构 * THINC Lab, School of Computing, University of Georgia（THINC实验室，计算学院，佐治亚大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen, Kenneth Marino, Rob Fergus

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2025

Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams

Ruoxin Xiong, Yanyu Wang, Suat Gunhan, Yimin Zhu, Charles Berryman

专题命中 记忆与上下文管理 ：workflow(abstract)；分类 cs.AI、cs.CL

Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning

Khanh Nguyen, Huy Hoang Nguyen, Egor Panfilov, Aleksei Tiulpin

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Improving World Models using Deep Supervision with Linear Probes

Andrii Zahorodnii

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2025 Workshop on World Models

Adapting World Models with Latent-State Dynamics Residuals

JB Lanier, Kyungmin Kim, Armin Karamzade, Yifei Liu, Ankita Sinha, Kat He, Davide Corsi, Roy Fox

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures. Project website at https://redraw.jblanier.net/

Application of Soft Actor-Critic Algorithms in Optimizing Wastewater Treatment with Time Delays Integration

Esmaeel Mohammadi, Daniel Ortiz-Arroyo, Aviaja Anna Hansen, Mikkel Stokholm-Bjerregaard, Sebastien Gros, Akhil S Anand, Petar Durdevic

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Expert Systems with Applications Volume 277, 5 June 2025, 127180

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

Zongyuan Zhang, Tianyang Duan, Zheng Lin, Dong Huang, Zihan Fang, Zekai Sun, Ling Xiong, Hongbin Liang, Heming Cui, Yong Cui, Yue Gao

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 6 figures

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

Zongyuan Zhang, Tianyang Duan, Zheng Lin, Dong Huang, Zihan Fang, Zekai Sun, Ling Xiong, Hongbin Liang, Heming Cui, Yong Cui

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Aly Lidayan, Michael Dennis, Stuart Russell

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at ICLR 2025

Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot

Ali Parsaee, Fahim Shahriar, Chuxin He, Ruiqing Tan

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at Alberta Robotics & Intelligent Systems Expo (RISE) Conference

Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints

Yuhao Zhou, Yuxin Tian, Jindi Lv, Mingjia Shi, Yuanxi Li, Qing Ye, Shuhao Zhang, Jiancheng Lv

专题命中 记忆与上下文管理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments CVPR 2025

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Matthew Renze, Erhan Guven

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.CL

Journal ref 2nd International Conference on Foundation and Large Language Models (FLLM 2024), pp. 476-483

AI-native Memory 2.0: Second Me

Jiale Wei, Xiang Ying, Tao Gao, Fangyi Bao, Felix Tao, Jingbo Shang

专题命中 记忆与上下文管理 ：AI agent(abstract)；分类 cs.AI、cs.CL

Accelerating Model-Based Reinforcement Learning with State-Space World Models

Maria Krinner, Elie Aljalbout, Angel Romero, Davide Scaramuzza

专题命中 记忆与上下文管理 ：planning(abstract)；分类 cs.AI、cs.LG

Learning To Explore With Predictive World Model Via Self-Supervised Learning

Alana Santana, Paula P. Costa, Esther L. Colombini

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Dynamic Reinforcement Learning for Actors

Katsunari Shibata

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 31 pages, 20 figures

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

Neeloy Chakraborty, Melkior Ornik, Katherine Driggs-Campbell

专题命中 记忆与上下文管理 ：planning(abstract)；分类 cs.AI、cs.CL

Comments Accepted to ACM Computing Surveys; 55 pages, 5 tables, 3 figures

Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control

Donghe Chen, Yubin Peng, Tengjie Zheng, Han Wang, Chaoran Qu, Lin Cheng

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages, 9 figures

Symbolic State Partitioning for Reinforcement Learning

Mohsen Ghaffari, Mahsa Varshosaz, Einar Broch Johnsen, Andrzej Wąsowski

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection

Bo Yang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.CL

Optimizing Automatic Differentiation with Deep Reinforcement Learning

Jamie Lohoff, Emre Neftci

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted as a spotlight paper at NeurIPS 2024

Journal ref Proceedings of the 38th Conference on Neural Information Processing Systems. 2024

The impact of intrinsic rewards on exploration in Reinforcement Learning

Aya Kayal, Eduardo Pignatelli, Laura Toni

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 45 pages, 17 figures. Submitted to Neural Computing and Applications Journal

Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation

Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, Tianyi Zhang, Kedi Xu, Aarav Bajaj, Ruslan Salakhutdinov, Matthew Johnson-Roberson, Yonatan Bisk

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Web: https://quanting-xie.github.io/Embodied-RAG-web/

Learning Constraint Network from Demonstrations via Positive-Unlabeled Learning with Memory Replay

Baiyu Peng, Aude Billard

专题命中 记忆与上下文管理 ：planning(abstract)；分类 cs.AI、cs.LG

Goal Recognition using Actor-Critic Optimization

Ben Nageris, Felipe Meneguzzi, Reuth Mirsky

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.AI、cs.LG

Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

Yuchen Fang, Yuxuan Liang, Bo Hui, Zezhi Shao, Liwei Deng, Xu Liu, Xinke Jiang, Kai Zheng

专题命中 记忆与上下文管理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted by SIGKDD 2025