AI Agent

Computing Machinery and Knowledge

Raymond Anneborg

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

Comments 7 pages

An Artificial Consciousness Model and its relations with Philosophy of Mind

Eduardo C. Garrido-Merchán, Martin Molina, Francisco M. Mendoza

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

DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting

Alessio Monti, Alessia Bertugli, Simone Calderara, Rita Cucchiara

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

Comments Accepted at ICPR 2020

Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards

Keyang He, Bikramjit Banerjee, Prashant Doshi

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

Comments 9 pages, 6 figures

TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments

Tom Bewley, Jonathan Lawry

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

Comments 12 pages (incl. references and appendices), 15 figures. Pre-print, under review

Evaluating recommender systems for AI-driven biomedical informatics

William La Cava, Heather Williams, Weixuan Fu, Steve Vitale, Durga Srivatsan, Jason H. Moore

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

Comments 17 pages, 8 figures. this version fixes link to pennai in abstract

Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges

Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, Natalia Díaz-Rodríguez

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

Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning

Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

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

Comments AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'19). arXiv admin note: text overlap with arXiv:1812.00045

Apply SOA Paradigms in Cyber-Physical System to Enhance Interoperability: State-of-the-Art Review

Su Zhang

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)；分类 cs.SE

Comments 6 pages, 0 figures

Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions

Upol Ehsan, Pradyumna Tambwekar, Larry Chan, Brent Harrison, Mark Riedl

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

Comments Accepted to the 2019 International Conference on Intelligent User Interfaces

Continual Match Based Training in Pommerman: Technical Report

Peng Peng, Liang Pang, Yufeng Yuan, Chao Gao

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

Comments 8 pages, 7 figures

Generative Temporal Models with Spatial Memory for Partially Observed Environments

Marco Fraccaro, Danilo Jimenez Rezende, Yori Zwols, Alexander Pritzel, S. M. Ali Eslami, Fabio Viola

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

Comments ICML 2018

Behavioral Cloning from Observation

Faraz Torabi, Garrett Warnell, Peter Stone

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

Comments International Joint Conference on Artificial Intelligence (IJCAI 2018)

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling

Christopher Schulze, Marcus Schulze

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

Comments 9 pages, 5 figures

A State-Based Regression Formulation for Domains with Sensing Actions<br> and Incomplete Information

Le-Chi Tuan, Chitta Baral, Tran Cao Son

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

Comments 34 pages, 7 Figures

Journal ref Logical Methods in Computer Science, Volume 2, Issue 4 (October 2, 2006) lmcs:2238

An Anytime Algorithm for Optimal Coalition Structure Generation

Talal Rahwan, Sarvapali Dyanand Ramchurn, Nicholas Robert Jennings, Andrea Giovannucci

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

Journal ref Journal Of Artificial Intelligence Research, Volume 34, pages 521-567, 2009

Flexible and Approximate Computation through State-Space Reduction

Weixiong Zhang

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

Comments Appears in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998)

Probabilistic State-Dependent Grammars for Plan Recognition

David V. Pynadath, Michael P. Wellman

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

Comments Appears in Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI2000)

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Gabriel Sarch, Yue Wu, Michael J. Tarr, Katerina Fragkiadaki

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

Comments Project page with code & videos: https://helper-agent-llm.github.io

Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection

Lucas N. Alegre, Ana L. C. Bazzan, Bruno C. da Silva

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

Comments Published at Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)

Journal ref Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems. 2021. 97-105

Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Zetta ζ：用于自进化物理智能的高效闭环具身框架

Xin Ding, Liang Mi, Mingzhe Huang, Zixuan Wang, Chao Zhang, Zixu Hao, Fu Chen, Xiangyu Li, Yikai Zheng, Yaoyu Guo, Weijun Wang, Kun Li, Hao Wu, Yunxin Liu, Ting Cao

机构 * Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR）） ； Z-Trans AI 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；agentic(abstract)

AI总结 Zetta ζ是一种闭环具身框架，通过时间尺度分离的循环进化评判器与恢复技能，结合Z-Infra在LIBERO-Pro、RoboCasa上实现90.8%、93.6%的成功率，为物理智能扩展提供路径。

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

FreeToken：面向边缘原生MoE服务的带宽自适应高效执行方案

Shuo Yang, Xiaoze Fan, Melissa Pan, Haocheng Xi, Zhe Wang, Shanlin Sun, Kurt Keutzer, Song Han, Matei Zaharia, Chenfeng Xu, Ion Stoica

专题命中 记忆与上下文管理 ：agent(abstract)；agentic(abstract)

AI总结 FreeToken是边缘原生MoE服务系统，通过协同设计服务栈实现带宽自适应执行，将个人计算机转化为弹性推理平台，可在边缘硬件上部署大参数MoE模型，拓展了本地AI服务能力。

DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving

DriveVLA-M0：面向自动驾驶的故障感知记忆增强方法

Zebin Xing, Yupeng Zheng, Qiang Chen, Linbo Wang, Yichen Zhang, Pengxuan Yang, Junli Wang, Deheng Qian, Xiaoqing Ye, Junyu Han, Yifeng Pan, Qichao Zhang, Dongbin Zhao

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Chongqing Chang’an Technology Co., Ltd.（重庆长安科技有限公司） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)

AI总结 本文提出DriveVLA-M0，一种具备故障感知潜在记忆的检索增强型VLA模型，通过故障案例记忆与针对性修正机制，在NAVSIM基准上优于现有方法，实现自动驾驶性能提升。

Compiling and Benchmarking Task-State Horizons for Embodied Agents

面向具身智能体的任务状态视界的编译与基准测试

Meiqi Wang, Shichao Li

专题命中 记忆与上下文管理 ：agent(abstract)；agentic(abstract)

AI总结 该研究定义任务状态视界（TSH），推出RoboGraph编译器并发布含588个情节的基准，发现多数先进智能体模型在高TSH下维护、更新任务相关状态存在差距。

Comments 32 pages, including appendices

MASS: Multiplayer World Models with Authoritative Shared State

MASS：具有权威共享状态的多人世界模型

Ziqi Cai, Siqi Yang, Yimu Wang, Zixian Gao, Yunheng Liu, Shuchen Weng, Erwin Wu, Kaipeng Zhang, Boxin Shi

机构 * Alaya Lab（Alaya实验室） ； Peking University（北京大学） ； Institute of Science Tokyo（东京科学大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；multi-agent(abstract)

AI总结 该研究提出MASS模型，通过将世界动态与视图渲染解耦，解决现有视频世界模型在多人环境中的缺陷，在多人Snake基准测试中实现更优状态精度，为多智能体世界模拟提供实用基础。

Comments Project Page: https://alaya-lab.github.io/MASS/

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks

WebChoreArena：在现实繁琐网页任务上评估网页浏览智能体

Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki

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

AI总结 本文提出WebChoreArena，作为WebArena的扩展，包含532个耗时300多小时开发的繁琐网页任务，从大规模记忆、计算、长期记忆三维度评估网页浏览智能体，实验显示其能清晰衡量LLM进展且难度高于WebArena。

Comments COLM2026. Project Page: https://webchorearena.github.io/

Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression

明确，而非冗长：什么使认知立场在记忆压缩中留存

Alex Kwon

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

AI总结 本研究探究使认知立场在记忆压缩中留存的因素，发现将立场表述为带标签的字段可提升留存率，明确立场而非仅延长表述是关键，明确的最佳方式取决于模型。

Comments 20 pages, 3 figures, 4 tables. Code, per-trial data, and the pre-registration commit: https://github.com/collapseindex/factwash

Mimir: A Neuro-Symbolic Memory System with Dynamic Grounding for Embodied Agents in Interactive Environments

Mimir：面向交互环境中具身智能体的、具备动态 grounding 的神经符号记忆系统

Haoming Xu, Zhenlin He, Hengyi Wang, Jiafeng Xu, Hao Dong

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)

AI总结 本文提出Mimir，一种分离世界与任务记忆并具备动态grounding的神经符号记忆系统，在EB-ALFRED、EB-Habitat等具身任务中显著提升了智能体的长程执行成功率。

Comments 9 pages, 4 figures

Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention

面向基于检索的稀疏注意力的通用近内存处理异构大语言模型服务

Hyungkyu Ham, Junhyeong Bae, Seungheon Lee, Myeongjae Jeon, Gwangsun Kim

专题命中 记忆与上下文管理 ：agentic(abstract,abstract_cn)

AI总结 本文针对前沿LLM的基于检索的稀疏注意力需求，提出异构解码服务系统KARAT，结合PNM与OFMS、CMR优化，大幅提升吞吐量与每TDP性能。

Safety Invariants for Agents Orchestrating Irreversible State Transitions: A Four-Dimensional Formalism Evaluated on Public Ledgers

编排不可逆状态转换的智能体的安全不变量：在公共账本上评估的四维形式主义

Zhaoming Yin

专题命中 记忆与上下文管理 ：agent(abstract)；autonomous agent(abstract)

AI总结 该研究针对编排不可逆状态转换的智能体，提出四维形式主义与七个安全不变量，在公共账本场景下验证其可提升智能体安全栈通过率，且可推广至其他不可逆状态交互场景。

Comments 29 pages, 8 figures, 7 tables