AI Agent

Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memory

Kunyao Lan, Bingrui Jin, Zichen Zhu, Siyuan Chen, Shu Zhang, Kenny Q. Zhu, Mengyue Wu

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

Combining AI Control Systems and Human Decision Support via Robustness and Criticality

Walt Woods, Alexander Grushin, Simon Khan, Alvaro Velasquez

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

Comments 19 pages, 12 figures

Journal ref Proc. SPIE 13058, Disruptive Technologies in Information Sciences VIII, 130580J (6 June 2024)

Mixed-Session Conversation with Egocentric Memory

Jihyoung Jang, Taeyoung Kim, Hyounghun Kim

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

Comments EMNLP Findings 2024 (30 pages); Project website: https://mixed-session.github.io/

Predictive Attractor Models

Ramy Mounir, Sudeep Sarkar

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

Comments Accepted to NeurIPS 2024

Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English

Fiifi Dawson, Zainab Mosunmola, Sahil Pocker, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat

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

Comments 19 pages, 10 figures, 6 tables

GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation

Brendan Hogan Rappazzo, Yingheng Wang, Aaron Ferber, Carla Gomes

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

Comments 8 pages

Learning to Play Video Games with Intuitive Physics Priors

Abhishek Jaiswal, Nisheeth Srivastava

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

Comments 7 pages, Accepted in Proceedings of the Annual Meeting of the Cognitive Science Society, Volume 46

Journal ref Proceedings of the Annual Meeting of the Cognitive Science Society, 46 (2024). Retrieved from https://escholarship.org/uc/item/92f5b1hk

Curricula for Learning Robust Policies with Factored State Representations in Changing Environments

Panayiotis Panayiotou, Özgür Şimşek

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

Comments 17th European Workshop on Reinforcement Learning (EWRL 2024)

Tractable Offline Learning of Regular Decision Processes

Ahana Deb, Roberto Cipollone, Anders Jonsson, Alessandro Ronca, Mohammad Sadegh Talebi

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

Comments To appear in EWRL 2024

An Idiosyncrasy of Time-discretization in Reinforcement Learning

Kris De Asis, Richard S. Sutton

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

Comments RLC 2024

AI-native Memory: A Pathway from LLMs Towards AGI

Jingbo Shang, Zai Zheng, Jiale Wei, Xiang Ying, Felix Tao, Mindverse Team

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

Online Electric Vehicle Charging Detection Based on Memory-based Transformer using Smart Meter Data

Ammar Mansoor Kamoona, Hui Song, Mahdi Jalili, Hao Wang, Reza Razzaghi, Xinghuo Yu

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

Imitation Learning for Intra-Day Power Grid Operation through Topology Actions

Matthijs de Jong, Jan Viebahn, Yuliya Shapovalova

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

Comments To be presented at the Machine Learning for Sustainable Power Systems 2024 workshop and to be published in the corresponding Springer Communications in Computer and Information Science proceedings

Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learning

Martin Holen, Per-Arne Andersen, Kristian Muri Knausgård, Morten Goodwin

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

Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations

Wei Pang, Ruixue Duan, Jinfu Yang, Ning Li

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

Comments This article has been accepted in CAAI Transactions on Intelligence Technology! Article ID: CIT2_12370, Article DOI: 10.1049/cit2.12370

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals

Grace Liu, Michael Tang, Benjamin Eysenbach

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

Comments Code and videos: https://graliuce.github.io/sgcrl/

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration

Dongyoung Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

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

Comments NeurIPS 2024. Project webpage: https://sites.google.com/view/rl-vcse

Empowering Private Tutoring by Chaining Large Language Models

Yulin Chen, Ning Ding, Hai-Tao Zheng, Zhiyuan Liu, Maosong Sun, Bowen Zhou

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

Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory

Mustafa Mert Çelikok, Frans A. Oliehoek, Jan-Willem van de Meent

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

Artificial Agency and Large Language Models

Maud van Lier, Gorka Muñoz-Gil

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

Comments Accepted for publication in journal Intellectica, special issue "Philosophies of AI: thinking and writing with LLMs" (Intellectica, issue 81)

Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess

Timo Bertram, Johannes Fürnkranz, Martin Müller

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

Comments Extended version of IEEE Conference on Games 2023 paper

Journal ref IEEE Transactions on Games 2024

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents

Menglong Zhang, Fuyuan Qian, Quanying Liu

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

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment

Heyan Huang, Yinghao Li, Huashan Sun, Yu Bai, Yang Gao

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

Comments 22 pages, 6 figures, work in progress

Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching

Kai Yan, Alexander G. Schwing, Yu-xiong Wang

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

Comments 25 pages. Accepted to ICML 2024

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Zelei Cheng, Xian Wu, Jiahao Yu, Sabrina Yang, Gang Wang, Xinyu Xing

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

Comments Accepted by ICML 2024

Toward Conversational Agents with Context and Time Sensitive Long-term Memory

Nick Alonso, Tomás Figliolia, Anthony Ndirango, Beren Millidge

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

How to Explore with Belief: State Entropy Maximization in POMDPs

Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti

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

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents

Safa Alver, Ali Rahimi-Kalahroudi, Doina Precup

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

Comments Published as a conference paper at CoLLAs 2024

Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation

Cheng Niu, Xingguang Wang, Xuxin Cheng, Juntong Song, Tong Zhang

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

ST-MambaSync: The Complement of Mamba and Transformers for Spatial-Temporal in Traffic Flow Prediction

Zhiqi Shao, Xusheng Yao, Ze Wang, Junbin Gao

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

Comments 11 pages. arXiv admin note: substantial text overlap with arXiv:2404.13257