AI Agent

Self-driving lab discovers principles for steering spontaneous emission

Saaketh Desai, Sadhvikas Addamane, Jeffery Y. Tsao, Igal Brener, Remi Dingreville, Prasad P. Iyer

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments 25 pages, 4 figures in main text, 5 figures in supplementary information

Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

Ali Hummos

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Comments Published ICLR 2023

Journal ref The Eleventh International Conference on Learning Representations 2023

Trust Your Gut: Comparing Human and Machine Inference from Noisy Visualizations

Ratanond Koonchanok, Michael E. Papka, Khairi Reda

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments To appear in IEEE Transactions on Visualization and Computer Graphics (Proceedings of IEEE VIS'24)

Distributed Difference of Convex Optimization

Vivek Khatana, Murti V. Salapaka

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Comments 9 pages, 7 figures

Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN

Norman Becker, Daniel Reti, Evridiki V. Ntagiou, Marcus Wallum, Hans D. Schotten

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

RobocupGym: A challenging continuous control benchmark in Robocup

Michael Beukman, Branden Ingram, Geraud Nangue Tasse, Benjamin Rosman, Pravesh Ranchod

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs

Chaoqun He, Renjie Luo, Shengding Hu, Yuanqian Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

专题命中 Agent评测 ：workflow(abstract)；分类 cs.CL

Comments Accepted by ACL 2024 System Demostration Track, update

Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization

Carolin Benjamins, Gjorgjina Cenikj, Ana Nikolikj, Aditya Mohan, Tome Eftimov, Marius Lindauer

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Journal ref GECCO 2024

Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions

Martín de Frutos, Oscar A. Marino, David Huergo, Esteban Ferrer

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark

Paul Daoudi, Bojan Mavkov, Bogdan Robu, Christophe Prieur, Emmanuel Witrant, Merwan Barlier, Ludovic Dos Santos

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Journal ref 2024 IEEE Conference on Control Technology and Applications (CCTA)

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents

Xing Han Lu, Siva Reddy, Harm de Vries

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL

Comments Accepted at EACL 2023

Journal ref Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. (2023) 2799-2829

The Effects of Embodiment and Personality Expression on Learning in LLM-based Educational Agents

Sinan Sonlu, Bennie Bendiksen, Funda Durupinar, Uğur Güdükbay

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL

Comments 15 pages, 4 figures, 3 tables

Share, Collaborate, Benchmark: Advancing Travel Demand Research through rigorous open-source collaboration

Juan D. Caicedo, Carlos Guirado, Marta C. González, Joan L. Walker

专题命中 Agent评测 ：planning(abstract)；分类 cs.LG

Comments 18 pages, 8 figures

Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods

Riccardo De Santi, Manish Prajapat, Andreas Krause

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments ICML 2024

GPT-4 is judged more human than humans in displaced and inverted Turing tests

Ishika Rathi, Sydney Taylor, Benjamin K. Bergen, Cameron R. Jones

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL

Continual Developmental Neurosimulation Using Embodied Computational Agents

Bradly Alicea, Rishabh Chakrabarty, Stefan Dvoretskii, Akshara Gopi, Avery Lim, Jesse Parent

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Comments 35 pages, 9 figures

Expanding continual few-shot learning benchmarks to include recognition of specific instances

Gideon Kowadlo, Abdelrahman Ahmed, Amir Mayan, David Rawlinson

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments Published in PLOS ONE https://doi.org/10.1371/journal.pone.0305856

Journal ref PLOS ONE, vol. 19, no. 7, p. e0305856, Jul. 2024

Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learning

Jakob Nyberg, Pontus Johnson

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Comments Accepted to IEEE CSR 2024

Over the Edge of Chaos? Excess Complexity as a Roadblock to Artificial General Intelligence

Teo Susnjak, Timothy R. McIntosh, Andre L. C. Barczak, Napoleon H. Reyes, Tong Liu, Paul Watters, Malka N. Halgamuge

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services

Maqsood Hussain Shah, Yue Ding, Shaoshu Zhu, Yingqi Gu, Mingming Liu

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Comments 15 pages, 5 figures

Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions

Hamza Keurti, Hsiao-Ru Pan, Michel Besserve, Benjamin F. Grewe, Bernhard Schölkopf

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments Accepted at ICML2023, Presented at the Symmetry and Geometry in Neural Representations Workshop (NeurReps) @ NeurIPS2022, 26 pages, 17 figures

Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators

Ori Linial, Guy Tennenholtz, Uri Shalit

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Toxic comments reduce the activity of volunteer editors on Wikipedia

Ivan Smirnov, Camelia Oprea, Markus Strohmaier

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL

On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems

Emiland Garrabe, Hozefa Jesawada, Carmen Del Vecchio, Giovanni Russo

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments 17 pages, 5 figures. An early version of this paper with only a sketch of the proof for one of the results and without the hardware validation was presentation at the 62nd IEEE Conference on Decision and Control. arXiv admin note: text overlap with arXiv:2303.17957

Fundamental Bounds on Online Strategic Classification

Saba Ahmadi, Avrim Blum, Kunhe Yang

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

EMMI -- Empathic Multimodal Motivational Interviews Dataset: Analyses and Annotations

Lucie Galland, Catherine Pelachaud, Florian Pecune

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL

Comments 9 pages

On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey

Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, Haobo Wang

专题命中 Agent评测 ：workflow(abstract)；分类 cs.CL

Comments A survey on LLMs-driven synthetic data generation, curation and evaluation

Evolution of Rewards for Food and Motor Action by Simulating Birth and Death

Yuji Kanagawa, Kenji Doya

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI

Impact of Decentralized Learning on Player Utilities in Stackelberg Games

Kate Donahue, Nicole Immorlica, Meena Jagadeesan, Brendan Lucier, Aleksandrs Slivkins

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Comments To appear at ICML 2024; this is the full version

MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards

Yuming Huang, Bin Ren, Ziming Xu, Lianghong Wu

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI