AI Agent - arXivDaily 专题

2307.09423 2024-12-20 cs.LG cs.AI stat.ML 81%

Scaling Laws for Imitation Learning in Single-Agent Games

Jens Tuyls, Dhruv Madeka, Kari Torkkola, Dean Foster, Karthik Narasimhan, Sham Kakade

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

Comments Accepted at TMLR 2024

2306.06909 2024-12-12 cs.LG cs.AI cs.CR cs.NE 81%

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

Ao Liu, Wenshan Li, Tao Li, Beibei Li, Guangquan Xu, Pan Zhou, Wengang Ma, Hanyuan Huang

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

2407.02483 2024-10-08 cs.CL cs.AI 81%

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent

Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, Yixin Wang

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

Comments EMNLP 2024

2408.08230 2024-08-16 cs.AI cs.LG 81%

Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators

Mark Towers, Yali Du, Christopher Freeman, Timothy J. Norman

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

Comments 7 pages + 3 pages of supplementary material. Published at ECAI 2024

Journal ref ECAI 2024

2404.08692 2024-04-16 cs.IR cs.AI cs.CL 81%

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

2403.04417 2024-03-08 cs.CL cs.AI cs.SY eess.SY math.DS 81%

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

2402.17546 2024-02-28 cs.AI cs.CL 81%

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

2401.02777 2024-01-31 cs.CL cs.AI 81%

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

2311.06330 2023-12-19 cs.AI cs.CE cs.CL cs.MA econ.GN q-fin.EC 81%

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

2309.02435 2023-09-06 cs.LG cs.AI cs.CV cs.NE cs.RO 81%

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/

2308.15214 2023-08-31 cs.CL cs.AI cs.HC cs.RO 81%

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

2305.05159 2023-05-10 cs.LG cs.AI cs.MA 81%

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

2211.07805 2023-05-09 cs.LG cs.AI 81%

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

2205.12295 2023-03-06 cs.NE cs.AI cs.AR cs.LG 81%

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

2203.05285 2022-10-20 cs.LG cs.AI cs.MA 81%

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

2210.02585 2022-10-07 cs.LG cs.AI 81%

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

2112.15236 2022-01-03 cs.LG cs.AI 81%

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

2110.00433 2021-10-04 cs.CL cs.AI 81%

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

2109.03331 2021-09-09 cs.CR cs.AI cs.LG 81%

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)

2103.09439 2021-03-18 cs.RO cs.AI cs.LG 81%

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

2010.12710 2020-10-27 cs.CL cs.CY cs.LG 81%

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

1905.04192 2019-05-13 cs.LG cs.AI cs.SD stat.ML 81%

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

1806.00540 2018-06-05 cs.LG cs.AI stat.ML 81%

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

1709.10163 2018-01-23 cs.AI cs.LG 81%

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

1201.6583 2012-02-01 cs.AI cs.LG 81%

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

2606.24775 2026-06-24 cs.CL cs.DB cs.IR 新提交 80%

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）

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

2509.00080 2025-09-03 cs.AI 80%

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）

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)

2506.20000 2025-06-26 cs.CR cs.DC cs.LG 80%

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）

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)

2504.07046 2025-04-10 cs.CV cs.CL 80%

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

2606.09900 2026-06-10 cs.CL cs.AI cs.IR cs.LG 新提交 80%

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）

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

1. 记忆与上下文管理 4758 篇

Scaling Laws for Imitation Learning in Single-Agent Games

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent

Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators

Apollonion: Profile-centric Dialog Agent

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

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

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

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

Efficient RL via Disentangled Environment and Agent Representations

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

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

Agent-State Construction with Auxiliary Inputs

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

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

Query The Agent: Improving sample efficiency through epistemic uncertainty estimation

Learning Agent State Online with Recurrent Generate-and-Test

External knowledge transfer deployment inside a simple double agent Viterbi algorithm

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

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

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

Do Autonomous Agents Benefit from Hearing?

Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling

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

Empowerment for Continuous Agent-Environment Systems

Are We Ready For An Agent-Native Memory System?

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

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

A Unified Agentic Framework for Evaluating Conditional Image Generation

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