AI Agent

Cost Sensitive Reachability Heuristics for Handling State Uncertainty

Daniel Bryce, Subbarao Kambhampati

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

Comments Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)

Optimizing Memory-Bounded Controllers for Decentralized POMDPs

Christopher Amato, Daniel S Bernstein, Shlomo Zilberstein

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

Comments Appears in Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007)

CORL: A Continuous-state Offset-dynamics Reinforcement Learner

Emma Brunskill, Bethany Leffler, Lihong Li, Michael L. Littman, Nicholas Roy

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

Comments Appears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008)

Neuroevolution Results in Emergence of Short-Term Memory for Goal-Directed Behavior

Konstantin Lakhman, Mikhail Burtsev

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

Comments Manuscript was submitted to the 12th International Conference on the Simulation of Adaptive Behavior 2012; 10 pages, 6 figures

The Ditmarsch Tale of Wonders - The Dynamics of Lying

Hans van Ditmarsch

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

Symbolic Dynamic Programming for Discrete and Continuous State MDPs

Scott Sanner, Karina Valdivia Delgado, Leliane Nunes de Barros

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

Consistency of Feature Markov Processes

Peter Sunehag, Marcus Hutter

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

Comments 16 LaTeX pages

Journal ref Proc. 21st International Conf. on Algorithmic Learning Theory (ALT-2010) pages 360-374

Compiling Causal Theories to Successor State Axioms and STRIPS-Like Systems

F. Lin

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

Journal ref Journal Of Artificial Intelligence Research, Volume 19, pages 279-314, 2003

The Automatic Inference of State Invariants in TIM

M. Fox, D. Long

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

Journal ref Journal Of Artificial Intelligence Research, Volume 9, pages 367-421, 1998

Distributed Constrained Optimization with Semicoordinate Transformations

William Macready, David Wolpert

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

The end of Sleeping Beauty's nightmare

Berry Groisman

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

Comments 7 pages, MSWord, to appear in The British Journal for the Philosophy of Science

Responsibility and blame: a structural-model approach

Hana Chockler, Joseph Y. Halpern

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

Definition and Complexity of Some Basic Metareasoning Problems

Vincent Conitzer, Tuomas Sandholm

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

Journal ref In Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI-03), Acapulco, Mexico, 2003

Towards a computational theory of human daydreaming

Erik T. Mueller, Michael G. Dyer

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

Comments 10 pages. Appears in: Proceedings of the Seventh Annual Conference of the Cognitive Science Society (pp. 120-129). Irvine, CA. 1985

Representing and Aggregating Conflicting Beliefs

Pedrito Maynard-Reid, Daniel Lehmann

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

Comments 19 pages, 5 figures, appears (without proofs) in Proceedings of the Seventh International Conference on Principles of Knowledge Representation and Reasoning (KR 2000)

Journal ref Proceedings of the Seventh International Conference on Principles of Knowledge Representation and Reasoning (KR 2000), April 2000, pp. 153-164

Learning Policies with External Memory

Leonid Peshkin, Nicolas Meuleau, Leslie Kaelbling

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

Comments 8 pages

Journal ref In Bratko, I., and Dzeroski, S., eds., Machine Learning: Proceedings of the Sixteenth International Conference, pp. 307-314. Morgan Kaufmann, San Francisco, CA

Investigating Distributions of Telecom Adapted Sentence Embeddings for Document Retrieval

Sujoy Roychowdhury, Sumit Soman, Ranjani Hosakere Gireesha, Vansh Chhabra, Neeraj Gunda, Subhadip Bandyopadhyay, Sai Krishna Bala

机构 * Ericsson R&D（爱立信研发） 纠错

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

Comments Accepted for the Workshop On Next Gen Networks Through LLMs Action Models and Multi Agent Systems at IEEE International Conference on Communications (ICC) 2025

Design and Development of an Automated Coimagination Support System

John Noel Victorino, Naoto Fukunaga, Tomohiro Shibata

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

Comments 6 pages, 9 figures, submitted to The 8th International Conference on Human-Agent Interaction (HAI 2020)

Cooperation and Self-Regulation in a Model of Agents Playing Different Games

H. Fort

专题命中 记忆与上下文管理 ：agent(abstract,comments)

Comments 11 pages, 3 figures, keybords: Complex adaptive systems, Agent-based models, Social systems

MGpi: A Computational Model of Multiagent Group Perception and Interaction

Navyata Sanghvi, Ryo Yonetani, Kris Kitani

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

Comments To be published in: Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020), May 2020, Auckland, New Zealand

Journal ref Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020), pp. 1196-1205

Automated Estimation of MBIST Area and Test Time in Heterogeneous Memory IPs via Stacked Ensemble Framework

基于堆叠集成框架的异构内存IP中MBIST面积与测试时间的自动化估算

Chee Jin Teoh, Ab Al-Hadi Ab Rahman, Johnny Kee Hui Wong, Premkumar A/L Kesavan Prabagaran, Muhammad Nadzir Marsono, Nuzhat Khan

专题命中 记忆与上下文管理 ：planning(abstract)

AI总结 本研究提出堆叠集成框架，基于RTL参数直接预测异构内存IP的MBIST面积与测试时间，准确率优于基线方法，可快速估算MBIST开销以支持高效设计决策。

Report on The 1st Workshop on Human-Centered Proactive and Personalized Agents for Interactive Information Access at CHIIR 2026

CHIIR 2026 第一届面向交互式信息获取的以人为中心的主动式与个性化智能体研讨会报告

Kirandeep Kaur, Vinayak Gupta, Tanya Roosta, Madhura Raju, Grace Hui Yang, Chirag Shah

专题命中 记忆与上下文管理 ：agentic(abstract)

AI总结 该报告总结了CHIIR 2026第一届相关研讨会，探讨交互式信息获取向主动个性化智能体转变的机遇与问题，明确主动的核心内涵并梳理出相关设计挑战。

Brief Announcement: Fair Binding for Hidden-State Authorization in Byzantine SMR

简短公告：拜占庭SMR中隐藏状态授权的公平绑定

Arnab Mallick

专题命中 记忆与上下文管理 ：agent(abstract)

AI总结 针对拜占庭SMR中隐藏状态授权问题，提出公平预留/使用协议，满足授权安全性与先到者活性，解决隐藏资源安全动态分配问题。

Comments Accepted at DISC 2026

Why This and Not That? A Collaborative Reflection Approach for Understanding Thought Coverage in Decision Making Support Dialog

为何选此而非彼？一种用于理解决策支持对话中思维覆盖的协作反思方法

Morita Tarvirdians, Hayley Hung, Catharine Oertel

专题命中 记忆与上下文管理 ：agent(abstract)

AI总结 该研究针对决策支持对话智能体的自适应策略易误判用户状态的问题，提出以人为中心的协作反思方法，经用户研究发现用户解释可指导更恰当的对话动作。

Estimating the growth in emissions from AI data centres

估算AI数据中心的排放增长

Wim Vanderbauwhede

专题命中 记忆与上下文管理 ：agentic(abstract)

AI总结 本研究采用先进生命周期评估模型，结合IEA与麦肯锡情景，量化AI数据中心扩张的排放，发现AI行业推崇的情景会使总排放大幅上升，隐含碳分量显著。

Comments 5 pages, 2 figures. Accepted at the 2nd International Workshop on Low Carbon Computing (LOCO 2026), Lancaster University, United Kingdom, 10-11 September 2026. Part of the LOCO 2026 proceedings, arXiv:LOCO2026/P05

Proof-of-Execution Memory: Defending LLM Agents Against Forged-Reasoning Attacks by Verifying What Actually Happened

执行证明内存：通过验证实际发生的内容防御大语言模型智能体的伪造推理攻击

Md Habibur Rahman, Jaeho Kim

专题命中 记忆与上下文管理 ：agent(abstract)

AI总结 该研究针对大语言模型智能体的伪造推理攻击，提出执行证明内存（PoEM）防御方案，通过维护防篡改的HMAC链式分类账验证实际执行步骤，使攻击成功率降至0%，且误报率极低、开销微小。

Comments 8 pages, 6 figures, 5 tables. Code: https://github.com/bithabib/ai_security

A memory-based three-state model of competing technology adoption: substitution regimes, multi-homing, and churn

基于记忆的技术竞争采纳三状态模型：替代机制、多归属与流失

Stefano Scialla, Marco Patriarca, Els Heinsalu, Julyan H. E. Cartwright

专题命中 记忆与上下文管理 ：agent(abstract)

AI总结 该研究提出基于记忆的三状态智能体竞争模型，可复现四类技术替代机制，揭示相似市场替代曲线或有不同微观成因，为关联技术替代轨迹与个体行为提供紧凑基线。

Comments 15 pages, 4 figures

MISO: Model-Internal-State-Guided Optimization for Ranking Models

MISO：面向排序模型的模型内部状态引导优化

Yongzhe Zhang, Xiaoyu Deng, Yifan He, Mengying Sun, Sheng Luo, Yijia Liu, Hao Yan, Zhuo Li, Huiping Yao, Swathi Hrishikesh, Jing Chen, Dennis Choi, Steven Liu, Zhiwen Chen, Yang Jin, Haoyu Zhou, Lexi Luo, Keyi Chen, Anish Khazane, Marcio Porto, Xiaoya Wang, Emmy Wang, Kangfu Zheng, Xingyuan Wang, Peggy Yao, Yi Meng, Bilal Fadlallah, Gursharan Singh, Prabhakar Goyal, Alireza Vahdatpour, Santanu Kolay

专题命中 记忆与上下文管理 ：workflow(abstract)

AI总结 针对排序模型优化依赖昂贵试错的问题，提出利用模型内部状态的MISO工作流，在广告排序案例中提升归一化熵且减少验证运行，实现手动调优与自动搜索的折中。

Comments Accepted at the OARS Workshop at ACM RecSys 2026

Revisiting ab-initio excited state forces from many-body Green's function formalism: approximations and benchmark

重新审视基于许多体格林函数方法的从头计算激发态力：近似与基准测试

Rafael R. Del Grande, David A. Strubbe

专题命中 记忆与上下文管理 ：workflow(abstract)

AI总结 本文基于GW/BSE和DFPT计算，重新审视激发态力方法，修正了Ismail-Beigi和Louie的实现问题，并改进了电子-声子系数近似，用于研究材料中分子的激子-声子相互作用。

An ergodic theorem for multi-period mutual insurance

多期相互保险的遍历定理

John Armstrong

专题命中 记忆与上下文管理 ：agent(abstract)

AI总结 该论文针对存在异质性风险且无不可保险系统性风险的市场，证明多期相互保险的遍历定理，提出仅用短期合约即可实现极限效用的机制，可应用于风险分摊经济体及保险产品设计。