AI Agent

Apollonion: Profile-centric Dialog Agent

Shangyu Chen, Zibo Zhao, Yuanyuan Zhao, Xiang Li

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

Promising and worth-to-try future directions for advancing state-of-the-art surrogates methods of agent-based models in social and health computational sciences

Atiyah Elsheikh

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

Comments 4 pages

COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt

Suyeon Lee, Jieun Kang, Harim Kim, Kyoung-Mee Chung, Dongha Lee, Jinyoung Yeo

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

Comments 4 pages, 2 figures

From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models

Na Liu, Liangyu Chen, Xiaoyu Tian, Wei Zou, Kaijiang Chen, Ming Cui

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

Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations

Zengqing Wu, Run Peng, Xu Han, Shuyuan Zheng, Yixin Zhang, Chuan Xiao

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

Comments Source codes are available at https://github.com/Roihn/SABM

Efficient RL via Disentangled Environment and Agent Representations

Kevin Gmelin, Shikhar Bahl, Russell Mendonca, Deepak Pathak

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

Comments ICML 2023. Website at https://sear-rl.github.io/

FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions

Neeraj Cherakara, Finny Varghese, Sheena Shabana, Nivan Nelson, Abhiram Karukayil, Rohith Kulothungan, Mohammed Afil Farhan, Birthe Nesset, Meriam Moujahid, Tanvi Dinkar, Verena Rieser, Oliver Lemon

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

Comments 5 pages, 2 figures, Accepted at SIGDIAL 2023 (24th Meeting of the Special Interest Group on Discourse and Dialogue), for the demo video, see https://youtu.be/fwtUl1kl22s

Latent Interactive A2C for Improved RL in Open Many-Agent Systems

Keyang He, Prashant Doshi, Bikramjit Banerjee

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

Agent-State Construction with Auxiliary Inputs

Ruo Yu Tao, Adam White, Marlos C. Machado

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

Comments Published in Transactions on Machine Learning Research. 13 pages + 2 references + 15 appendix, 12 figures

lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents

Rachmad Vidya Wicaksana Putra, Muhammad Shafique

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

Comments To appear at the 2022 International Joint Conference on Neural Networks (IJCNN), the 2022 IEEE World Congress on Computational Intelligence (WCCI), July 2022, Padova, Italy

Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework

Xiaotian Hao, Hangyu Mao, Weixun Wang, Yaodong Yang, Dong Li, Yan Zheng, Zhen Wang, Jianye Hao

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

Query The Agent: Improving sample efficiency through epistemic uncertainty estimation

Julian Alverio, Boris Katz, Andrei Barbu

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

Comments Submitted to ICLR 2023

Learning Agent State Online with Recurrent Generate-and-Test

Amir Samani, Richard S. Sutton

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

External knowledge transfer deployment inside a simple double agent Viterbi algorithm

Zied Baklouti

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

CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems

Li Li, Raed Fayad, Adrian Taylor

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

Comments Presented at 1st International Workshop on Adaptive Cyber Defense, 2021 (arXiv:2108.08476)

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

Zhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki

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

Improving Classification through Weak Supervision in Context-specific Conversational Agent Development for Teacher Education

Debajyoti Datta, Maria Phillips, Jennifer Chiu, Ginger S. Watson, James P. Bywater, Laura Barnes, Donald Brown

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

Comments Preprint: Under Review

Do Autonomous Agents Benefit from Hearing?

Abraham Woubie, Anssi Kanervisto, Janne Karttunen, Ville Hautamaki

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

Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling

Kenny J. Young, Richard S. Sutton, Shuo Yang

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

Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces

Garrett Warnell, Nicholas Waytowich, Vernon Lawhern, Peter Stone

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

Comments 9 pages, 6 figures

Empowerment for Continuous Agent-Environment Systems

Tobias Jung, Daniel Polani, Peter Stone

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

Journal ref Adaptive Behavior 19(1),2011

Are We Ready For An Agent-Native Memory System?

我们准备好构建原生智能体记忆系统了吗？

Wei Zhou, Xuanhe Zhou, Shaokun Han, Hongming Xu, Guoliang Li, Zhiyu Li, Feiyu Xiong, Fan Wu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tsinghua University（清华大学） ； MemTensor (Shanghai) Technology Co., Ltd（MemTensor（上海）科技有限公司） 纠错

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

AI总结 从数据管理视角系统研究智能体记忆，提出四模块分析框架，评估12种记忆系统，发现无单一架构占优，并揭示成本-性能权衡。

Comments Paper list available at: https://github.com/OpenDataBox/awesome-agent-memory. Source code available at: https://github.com/OpenDataBox/MemoryData

Wrong Face, Wrong Move: The Social Dynamics of Emotion Misperception in Agent-Based Models

David Freire-Obregón

机构 * SIANI, Universidad de Las Palmas de Gran Canaria, Spain（SIANI，拉斯帕尔马斯德Gran Canaria大学，西班牙） 纠错

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

Comments Accepted for presentation at the International Workshop on Agent-Based Modelling of Human Behaviour (ABMHuB 2025)

Can One Safety Loop Guard Them All? Agentic Guard Rails for Federated Computing

Narasimha Raghavan Veeraragavan, Jan Franz Nygård

机构 * Division of Cancer Registry of Norway, Norwegian Institute of Public Health, Oslo, Norway（挪威癌症登记处，挪威公共卫生研究所，奥斯陆） ； Department of Physics and Technology, The Arctic University of Norway, Tromsø, Norway（挪威极地大学物理与技术系） 纠错

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

Comments Accepted at ICML 2025 Workshop on Collaborative and Federated Agentic Workflows (CFAgentic@ICML'25)

A Unified Agentic Framework for Evaluating Conditional Image Generation

Jifang Wang, Xue Yang, Longyue Wang, Zhenran Xu, Yiyu Wang, Yaowei Wang, Weihua Luo, Kaifu Zhang, Baotian Hu, Min Zhang

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

Comments Work in progress. GitHub: https://github.com/HITsz-TMG/Agentic-CIGEval

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

更少上下文，更高准确率：一种用于LLM Agent的双时间记忆引擎，其中精简检索上下文优于完整历史

Liuyin Wang

机构 * Independent Researcher（独立研究者） 纠错

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

AI总结 提出一种双时间记忆引擎Engram，通过混合读取路径从约9.6k token的检索片段中回答，在LongMemEval_S上达到83.6%准确率，比完整历史（79k token）高10.4个百分点，且无错误。

Comments 14 pages, 4 figures, 3 tables. Code, reproducible harness, and raw per-question logs: https://github.com/ly-wang19/engram

M$^\star$: Every Task Deserves Its Own Memory Harness

M$^\star$：每个任务都应有专属的记忆框架

Wenbo Pan, Shujie Liu, Xiangyang Zhou, Shiwei Zhang, Wanlu Shi, Mirror Xu, Xiaohua Jia

机构 * City University of Hong Kong（香港城市大学） ； Microsoft（微软） 纠错

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

AI总结 提出M$^\star$方法，通过可执行程序进化自动发现任务优化的记忆系统，在对话、具身规划和专家推理等任务上优于固定记忆基线。

Comments Preprint. Code: https://github.com/wbopan/mstar ; Live demo: https://mstar.wenbo.io

Personal Visual Context Learning in Large Multimodal Models

个人视觉上下文学习在大型多模态模型中

Zihui Xue, Ami Baid, Sangho Kim, Mi Luo, Kristen Grauman

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

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

AI总结 本文提出个人视觉上下文学习（Personal VCL）以解决个性化查询，通过Personal-VCL-Bench评估，发现现有模型在利用视觉证据和聚合多视觉观察方面存在显著不足，提出Agentic Context Bank方法提升性能。

Comments Project website: https://vision.cs.utexas.edu/projects/PersonalVCL/

El Agente Sólido: A New Age(nt) for Solid State Simulations

固态代理：固态模拟的新时代

Sai Govind Hari Kumar, Yunheng Zou, Andrew Wang, Jesús Valdés-Hernández, Tsz Wai Ko, Nathan Yue, Olivia Leng, Hanyong Xu, Chris Crebolder, Alán Aspuru-Guzik, Varinia Bernales

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

AI总结 El Agente Sólido是一种基于多代理框架的自动化固态量子化学模拟工具，结合密度泛函理论与机器学习势能，提升材料发现的效率和可重复性。

Comments 42 pages, 31 figures, 18 tables

RocqSmith: Can Automatic Optimization Forge Better Proof Agents?

RocqSmith: 自动优化能否打造更优的证明代理？

Andrei Kozyrev, Nikita Khramov, Denis Lochmelis, Valerio Morelli, Gleb Solovev, Anton Podkopaev

机构 * JetBrains Research Germany（JetBrains德国研究机构） ； JetBrains Research Netherlands（JetBrains荷兰研究机构） ； Constructor University Bremen（布雷梅Constructor大学） 纠错

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

AI总结 RocqSmith研究自动优化方法在提升证明代理性能上的效果，发现简单引导方法效果最佳，但无法超越精心设计的证明代理。