AI Agent - arXivDaily 专题

1903.05812 2024-03-28 math.OC 67%

Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information

Bora Yongacoglu, Gürdal Arslan, Serdar Yüksel

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

Journal ref IEEE Transactions on Automatic Control, vol. 67, no. 10, pp. 5230-5245, Oct. 2022

2403.14690 2024-03-25 cs.CY cs.AI cs.CL cs.LG 67%

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

Xiuqin Zhong, Shengyuan Yan, Gongqi Lin, Hongguang Fu, Liang Xu, Siwen Jiang, Lei Huang, Wei Fang

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

2402.17753 2024-02-28 cs.CL cs.AI cs.LG 67%

Evaluating Very Long-Term Conversational Memory of LLM Agents

Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, Yuwei Fang

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

Comments 19 pages; Project page: https://snap-research.github.io/locomo/

2402.09939 2024-02-16 cs.AI cs.CL cs.HC cs.IR cs.LG 67%

Generative AI in the Construction Industry: A State-of-the-art Analysis

Ridwan Taiwo, Idris Temitope Bello, Sulemana Fatoama Abdulai, Abdul-Mugis Yussif, Babatunde Abiodun Salami, Abdullahi Saka, Tarek Zayed

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

Comments 74 pages, 11 figures, 20 tables

2402.03890 2024-02-07 physics.soc-ph 67%

The Emergence of Cooperation in the well-mixed Prisoner's Dilemma: Memory Couples Individual and Group Strategies

Changyan Di, Jianyue Guan, Qingguo Zhou, Jingqiang Wang, Xiangyang Li

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

2309.12081 2024-01-17 eess.SY cs.SY 67%

A Framework on Fully Distributed State Estimation and Cooperative Stabilization of LTI Plants

Peihu Duan, Yuezu Lv, Guanghui Wen, Maciej Ogorzałek

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

2311.05584 2023-11-10 cs.LG cs.AI cs.CL 67%

Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations

Joey Hong, Sergey Levine, Anca Dragan

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

Comments 25 pages, 6 figures

2306.09312 2023-10-30 cs.LG cs.AI cs.CL stat.ML 67%

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter

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

Comments To appear at NeurIPS 2023, 10 pages (+ references and appendix), Code: https://github.com/ml-jku/helm

2210.01232 2023-10-30 eess.SY cs.SY 67%

Split-Spectrum Based Distributed State Estimation for Linear Systems

Lili Wang, Ji Liu, Brian B. O. Anderson, A. Stephen Morse

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

Comments 17 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:1903.05486

2308.11816 2023-10-18 cond-mat.mtrl-sci 67%

Assessing Thermodynamic Selectivity of Solid-State Reactions for the Predictive Synthesis of Inorganic Materials

Matthew J. McDermott, Brennan C. McBride, Corlyn Regier, Gia Thinh Tran, Yu Chen, Adam A. Corrao, Max C. Gallant, Gabrielle E. Kamm, Christopher J. Bartel, Karena W. Chapman, Peter G. Khalifah, Gerbrand Ceder, James R. Neilson, Kristin A. Persson

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

Comments Minor revisions (updated abstract, added discussion, added precursor purities, formatting). The first two authors contributed equally to this work. 53 pages, 7 figures

2304.03286 2023-10-18 cond-mat.stat-mech cs.IT math.IT nlin.CG physics.bio-ph q-bio.QM 67%

Semantic Information in a model of Resource Gathering Agents

Damian R Sowinski, Jonathan Carroll-Nellenback, Robert N Markwick, Jordi Piñero, Marcelo Gleiser, Artemy Kolchinsky, Gourab Ghoshal, Adam Frank

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

Comments 17 pages, 10 figures, 5 appendices

Journal ref PRX Life 1, 023003 (2023)

2303.11366 2023-10-11 cs.AI cs.CL cs.LG 67%

Reflexion: Language Agents with Verbal Reinforcement Learning

Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao

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

Comments v4 contains a few additional experiments

2309.00139 2023-09-04 math.OC 67%

On Privacy Preservation of Electric Vehicle Charging Control via State Obfuscation

Xiang Huo, Mingxi Liu

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

2302.12161 2023-08-31 eess.SY cs.SY math.OC 67%

Distributed State Estimation for Jointly Observable Linear Systems over Time-varying Networks

Shimin Wang, Martin Guay

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

Comments 12 pages,12 figures

2308.12445 2023-08-25 cs.LG cs.AI cs.SE stat.ML 67%

An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems

Ahmed Haj Yahmed, Rached Bouchoucha, Houssem Ben Braiek, Foutse Khomh

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

Comments Accepted for publication in The 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)

2307.11922 2023-07-25 cs.LG cs.AI cs.CL 67%

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Kolby Nottingham, Yasaman Razeghi, Kyungmin Kim, JB Lanier, Pierre Baldi, Roy Fox, Sameer Singh

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

2306.15605 2023-06-28 cs.RO 67%

Deep Normalizing Flows for State Estimation

Harrison Delecki, Liam A. Kruse, Marc R. Schlichting, Mykel J. Kochenderfer

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

Comments Accepted to FUSION 2023

2305.17144 2023-06-02 cs.AI cs.CL cs.CV cs.LG 67%

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, Yu Qiao, Zhaoxiang Zhang, Jifeng Dai

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

2302.03096 2023-06-01 cs.NE physics.soc-ph q-bio.PE 67%

The Struggle for Existence: Time, Memory and Bloat

John C Stevenson

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

Comments 1 table, 4 figures, 1 PDL

2305.18449 2023-05-31 cs.AI cs.CL cs.LG cs.SY eess.SY 67%

Taming AI Bots: Controllability of Neural States in Large Language Models

Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu

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

Comments TLDR: AI Bots are stochastic dynamical systems whose mental state can be controlled by both the user and the designer. The space of meanings, defined as equivalence classes of sentences, is learned during fine-tuning with human supervision, and safeguarding can be designed into the bot by establishing controls both at its input and output

2305.08291 2023-05-16 cs.AI cs.CL cs.CV cs.LG cs.NE 67%

Large Language Model Guided Tree-of-Thought

Jieyi Long

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

2301.01398 2023-01-05 cs.MA cs.RO cs.SY eess.SY 67%

Cost Inference for Feedback Dynamic Games from Noisy Partial State Observations and Incomplete Trajectories

Jingqi Li, Chih-Yuan Chiu, Lasse Peters, Somayeh Sojoudi, Claire Tomlin, David Fridovich-Keil

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

Comments Accepted by AAMAS 2023. This is a preprint version

2209.01888 2023-01-02 eess.SY cs.SY math.OC 67%

Event-Triggered l2-Optimal Formation Control with State-Estimation for Agents Modeled as LPV Systems

Gerald Gebhardt, Hamideh Saadabadi, Herbert Werner

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

Comments CDC 2022

2212.03279 2022-12-13 cs.AI cs.CL cs.LG 67%

From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems

Tom Young

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

Comments PhD thesis

2209.09900 2022-09-21 cs.CL cs.AI cs.LG 67%

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

Andy Rosenbaum, Saleh Soltan, Wael Hamza, Yannick Versley, Markus Boese

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

Comments Accepted to The 29th International Conference on Computational Linguistics (COLING 2022) October 12-17, 2022, Gyeongju, Republic of Korea https://coling2022.org/

2209.07392 2022-09-16 cs.RO 67%

On the programming effort required to generate Behavior Trees and Finite State Machines for robotic applications

Matteo Iovino, Julian Förster, Pietro Falco, Jen Jen Chung, Roland Siegwart, Christian Smith

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

Comments Submitted to 2023 IEEE International Conference on Robotics and Automation (ICRA)

2204.00199 2022-09-16 math.OC 67%

Reaching a Consensus with Limited Information

Jingxuan Zhu, Yixuan Lin, Ji Liu, A. Stephen Morse

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

Comments an expanded version of an accepted CDC paper

2101.06374 2022-03-29 cs.RO 67%

TridentNet: A Conditional Generative Model for Dynamic Trajectory Generation

David Paz, Hengyuan Zhang, Henrik I. Christensen

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

Comments 13 pages, 6 figures, IAS-16

2105.10099 2022-02-21 econ.TH econ.GN q-fin.EC 67%

Learning from zero: how to make consumption-saving decisions in a stochastic environment with an AI algorithm

Rui, Shi

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

2112.13560 2022-01-04 cs.MA 67%

A Survey of Event-triggered Control for Nonlinear Multiagent Systems with Guaranteed Steady-State Performance

Gurmu Meseret Debele

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

1. 记忆与上下文管理 4786 篇

Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

Evaluating Very Long-Term Conversational Memory of LLM Agents

Generative AI in the Construction Industry: A State-of-the-art Analysis

The Emergence of Cooperation in the well-mixed Prisoner's Dilemma: Memory Couples Individual and Group Strategies

A Framework on Fully Distributed State Estimation and Cooperative Stabilization of LTI Plants

Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Split-Spectrum Based Distributed State Estimation for Linear Systems

Assessing Thermodynamic Selectivity of Solid-State Reactions for the Predictive Synthesis of Inorganic Materials

Semantic Information in a model of Resource Gathering Agents

Reflexion: Language Agents with Verbal Reinforcement Learning

On Privacy Preservation of Electric Vehicle Charging Control via State Obfuscation

Distributed State Estimation for Jointly Observable Linear Systems over Time-varying Networks

An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Deep Normalizing Flows for State Estimation

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

The Struggle for Existence: Time, Memory and Bloat

Taming AI Bots: Controllability of Neural States in Large Language Models

Large Language Model Guided Tree-of-Thought

Cost Inference for Feedback Dynamic Games from Noisy Partial State Observations and Incomplete Trajectories

Event-Triggered l2-Optimal Formation Control with State-Estimation for Agents Modeled as LPV Systems

From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

On the programming effort required to generate Behavior Trees and Finite State Machines for robotic applications

Reaching a Consensus with Limited Information

TridentNet: A Conditional Generative Model for Dynamic Trajectory Generation

Learning from zero: how to make consumption-saving decisions in a stochastic environment with an AI algorithm

A Survey of Event-triggered Control for Nonlinear Multiagent Systems with Guaranteed Steady-State Performance