AI Agent

Dynamically writing coupled memories using a reinforcement learning agent, meeting physical bounds

Théo Jules, Laura Michel, Adèle Douin, Frédéric Lechenault

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

Comments Main text: 5 pages, 4 figures. Submitted to PNAS

GATSBI: Generative Agent-centric Spatio-temporal Object Interaction

Cheol-Hui Min, Jinseok Bae, Junho Lee, Young Min Kim

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

Comments accepted to CVPR'2021 as an oral presentation. Code and video will be released soon

Temporal Memory Relation Network for Workflow Recognition from Surgical Video

Yueming Jin, Yonghao Long, Cheng Chen, Zixu Zhao, Qi Dou, Pheng-Ann Heng

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

Comments Accepted at IEEE Transactions on Medical Imaging (IEEE TMI); Code is available at https://github.com/YuemingJin/TMRNet

Deep Context Maps: Agent Trajectory Prediction using Location-specific Latent Maps

Igor Gilitschenski, Guy Rosman, Arjun Gupta, Sertac Karaman, Daniela Rus

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

Deep RL Agent for a Real-Time Action Strategy Game

Michal Warchalski, Dimitrije Radojevic, Milos Milosevic

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

Adversarial recovery of agent rewards from latent spaces of the limit order book

Jacobo Roa-Vicens, Yuanbo Wang, Virgile Mison, Yarin Gal, Ricardo Silva

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

Comments Published as a workshop paper on NeurIPS 2019 Workshop on Robust AI in Financial Services. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning

Zhuoxuan Jiang, Ziming Huang, Dong Sheng Li, Xian-Ling Mao

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

Comments Under review

Data assimilation in Agent-based models using creation and annihilation operators

Daniel Tang

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

Pluggable Social Artificial Intelligence for Enabling Human-Agent Teaming

J. van Diggelen, J. S. Barnhoorn, M. M. M. Peeters, W. van Staal, M. L. Stolk, B. van der Vecht, J. van der Waa, J. M. Schraagen

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

Comments presented at NATO HFM symposium on Human Autonomy Teaming, Portsmouth, October 2018

Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling

Thomy Phan, Lenz Belzner, Marie Kiermeier, Markus Friedrich, Kyrill Schmid, Claudia Linnhoff-Popien

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

Comments Presented at AAAI 2019

An IoT Analytics Embodied Agent Model based on Context-Aware Machine Learning

Nathalia Nascimento, Paulo Alencar, Carlos Lucena, Donald Cowan

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

Comments 6 pages. arXiv admin note: substantial text overlap with arXiv:1802.03858

Unsupervised Predictive Memory in a Goal-Directed Agent

Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap

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

Nintendo Super Smash Bros. Melee: An "Untouchable" Agent

Ben Parr, Deepak Dilipkumar, Yuan Liu

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

Performance Limits of Stochastic Sub-Gradient Learning, Part I: Single Agent Case

Bicheng Ying, Ali H. Sayed

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

Comments Part II is available on http://arxiv.org/abs/1704.06025

Memory Lens: How Much Memory Does an Agent Use?

Christoph Dann, Katja Hofmann, Sebastian Nowozin

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

Comments Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems

Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems

Chien-Ju Ho, Aleksandrs Slivkins, Jennifer Wortman Vaughan

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

Comments This is the full version of a paper in the ACM Conference on Economics and Computation (ACM-EC), 2014

Investigating Mathematical Models of Immuno-Interactions with Early-Stage Cancer under an Agent-Based Modelling Perspective

Grazziela P. Figueredo, Peer-Olaf Siebers, Uwe Aickelin

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

Journal ref BMC Bioinformatics 14(Suppl 6), S6, 2013

A Dynamic Framework of Reputation Systems for an Agent Mediated e-market

Vibha Gaur, Neeraj Kumar Sharma

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

Comments 19 Pages; International Journal of Computer Science Issues (IJCSI),Vol 8, Issue 4, July 2011, ISSN(online): 1694-0814

How Emotional Mechanism Helps Episodic Learning in a Cognitive Agent

Usef Faghihi, Philippe Fournier-Viger, Roger Nkambou, Pierre Poirier, Andre Mayers

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

Agent-based Ecological Model Calibration - on the Edge of a New Approach

Antonio Pereira, Pedro Duarte, Luis Paulo Reis

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

Comments 7 pages, 6 figures, Proceedings of the International Conference on Knowledge Engineering and Decision Support, pp. 107-113, ISEP, Porto, Portugal, July 2004

Agent Models of Political Interactions

Eric Engle

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

Comments 22 pages

Fast and Memory Efficient Multimodal Journey Planning with Delays

快速且内存高效的考虑延迟的多模式行程规划

Denys Katkalo, Andrii Rohovyi, Toby Walsh

专题命中 记忆与上下文管理 ：planning(title,abstract)

AI总结 本文提出一种更高效、快速且准确的多模式行程规划方法，适用于单目标和双目标场景，通过优化算法提升速度和精度。

Comments v4: revised manuscript incorporating reviewer feedback (Related Work restructure, temporal-planning baselines, Bez 2020 thesis acknowledgment, equation relocation); style switched to the AAAI 2026 format

Taking Flight with Dialogue: Enabling Natural Language Control for PX4-based Drone Agent

Shoon Kit Lim, Melissa Jia Ying Chong, Jing Huey Khor, Ting Yang Ling

机构 * University of Southampton Malaysia（英国南安普顿大学马来西亚分校） ； Connected Intelligence Research Group（连接智能研究组） ； Sustainable Electronic Technologies（可持续电子技术） 纠错

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

Comments Source code available at: https://github.com/limshoonkit/ros2-agent-ws

Consentaneous agent-based and stochastic model of the financial markets

V. Gontis, A. Kononovicius

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 17 pages, 6 figures, Gontis V, Kononovicius A (2014) Consentaneous Agent-Based and Stochastic Model of the Financial Markets. PLoS ONE 9(7): e102201. doi: 10.1371/journal.pone.0102201

Journal ref PLoS ONE 9(7), e102201, 2014

DocAtlas: Long-Document Understanding as Mutable-State Interaction

DocAtlas：将长文档理解视为可变状态交互

Hongchen Wei, Yuanzhe Wang, Bei Liu, Yifan Yang, Qi Dai, Kai Qiu, Yunsheng Li, Dongdong Chen, Chong Luo, Zhenzhong Chen, Baining Guo

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

AI总结 本研究提出DocAtlas系统，将长文档理解视为可变状态交互，通过可变文档工具结合自改进检索等技术，在MMLongBench-Doc上用GPT-5.4达71.4%，还可提升紧凑型VLM智能体性能。

Toward Learning POMDPs Beyond Full-Rank Actions and State Observability

迈向超越全秩动作和状态可观测性的POMDP学习

Seiji Shaw, Travis Manderson, Chad Kessens, Nicholas Roy

机构 * MIT Computer Science and Artificial Intelligence Lab（麻省理工学院计算机科学与人工智能实验室） ； DEVCOM Army Research Laboratory（陆军研究实验室） 纠错

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

AI总结 本文提出了一种基于PSR方法学习POMDP参数的方法，通过张量分解估计相似变换，实现状态划分下的转移和观察模型学习，并展示了其在不同奖励函数下的应用潜力。

Comments WAFR camera-ready

OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis

OpsMem：用于故障诊断的具有跨内存共振的双内存推理

Yongqian Sun, Rongchen Gao, Yu Luo, Wenwei Gu, Shenglin Zhang, Qingyi Guo, Qiuai Fu, Yaoliang Wu, Dan Pei

机构 * Huawei（华为） 纠错

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

AI总结 针对现代软件系统故障诊断中缺乏协调诊断状态与操作经验机制的问题，提出双内存框架OpsMem，通过跨内存共振等进行多智能体诊断，实验表明其在华为微服务故障诊断数据集上优于基线，提升了匹配度和相关性。

Comments 6 pages, 5 figures

PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates

用于具有投影视图和经过验证的结构化更新的共享状态大语言模型工作流的PatchOptic

Zhaoyu Bai, Jiaqi Cai

机构 * Weizmann Institute of Science（魏茨曼科学研究所） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

AI总结 研究共享状态大语言模型工作流问题，提出受光学启发的PatchOptic接口，通过投影读取和验证结构化补丁实现，经PatchBench评估，该设计能减少泄漏和成本，保持输出质量，阻止违规并拒绝受损补丁。

Comments 24 pages, 13 figures, including appendix

CaveAgent: Transforming LLMs into Stateful Runtime Operators

CaveAgent：将LLM转变为具有状态的运行时操作符

Maohao Ran, Zhenglin Wan, Cooper Lin, Yanting Zhang, Hongyu Xin, Hongwei Fan, Yibo Xu, Beier Luo, Yaxin Zhou, Wangbo Zhao, Lijie Yang, Lang Feng, Fuchao Yang, Jingxuan Wu, Yiqiao Huang, Chendong Ma, Yusen Huang, Dailing Jiang, Jianbo Deng, Sirui Han, Yang You, Bo An, Yike Guo, Jun Song

机构 * Hong Kong Generative AI Research and Development Center (HKGAI)（香港生成式AI研究与开发中心（HKGAI）） 纠错

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

AI总结 CaveAgent通过引入双流架构，将LLM从文本生成器转变为运行时操作符，解决了长周期任务中上下文漂移问题，提升了多轮交互的稳定性和数据处理能力。

Comments ver.2

Mem-$π$: Adaptive Memory through Learning When and What to Generate

Mem-$π$: 通过学习何时以及生成什么来实现自适应记忆

Xiaoqiang Wang, Chao Wang, Hadi Nekoei, Christopher Pal, Alexandre Lacoste, Spandana Gella, Bang Liu, Perouz Taslakian

机构 * ServiceNow AI Research（ServiceNow AI研究院） ； Mila -- Quebec AI Institute（魁北克AI研究所） ； McGill University（麦吉尔大学） ； CIFAR AI Chair（CIFAR人工智能主席） 纠错

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

AI总结 Mem-$π$ 通过学习在何时以及生成什么来实现自适应记忆，利用专门的语言或视觉-语言模型生成上下文特定的指导，从而在多种代理任务中优于基于检索和先前RL优化的记忆基线。

Comments Work in progress