AI Agent

Monte Carlo Tree Search with Boltzmann Exploration

Michael Painter, Mohamed Baioumy, Nick Hawes, Bruno Lacerda

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Camera ready version of NeurIPS2023 paper

Journal ref Advances in Neural Information Processing Systems 36 (2024)

Tree Search-Based Policy Optimization under Stochastic Execution Delay

David Valensi, Esther Derman, Shie Mannor, Gal Dalal

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in ICLR 2024

DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model

Lirui Zhao, Yue Yang, Kaipeng Zhang, Wenqi Shao, Yuxin Zhang, Yu Qiao, Ping Luo, Rongrong Ji

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

Comments Published as a conference paper at CVPR 2024

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models

Wei He, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

专题命中 工具调用 ：tool-use(abstract)；分类 cs.AI、cs.CL

Comments Accepted to NAACL 2024 Findings

Learning-Based Algorithms for Graph Searching Problems

Adela Frances DePavia, Erasmo Tani, Ali Vakilian

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments AISTATS 2024

Llemma: An Open Language Model For Mathematics

Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Q. Jiang, Jia Deng, Stella Biderman, Sean Welleck

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.CL

Comments Updated references; corrected description of COPRA search budget

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taïga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, Rishabh Agarwal

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.CL

Comments In ICLR'24

OMNI: Open-endedness via Models of human Notions of Interestingness

Jenny Zhang, Joel Lehman, Kenneth Stanley, Jeff Clune

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 47 pages, 33 figures

Continuous Monte Carlo Graph Search

Kalle Kujanpää, Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at AAMAS 2024 (full paper & oral)

Curriculum reinforcement learning for quantum architecture search under hardware errors

Yash J. Patel, Akash Kundu, Mateusz Ostaszewski, Xavier Bonet-Monroig, Vedran Dunjko, Onur Danaci

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 32 pages, 11 figures, 6 tables. Accepted at ICLR 2024

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

Shibo Hao, Tianyang Liu, Zhen Wang, Zhiting Hu

专题命中 工具调用 ：tool use(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2023 (oral). Code: https://github.com/Ber666/ToolkenGPT

Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials

Janosh Riebesell, T. Wesley Surta, Rhys Goodall, Michael Gaultois, Alpha A Lee

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.LG

Comments 27 pages, 11 figures, 5 authors

ECGformer: Leveraging transformer for ECG heartbeat arrhythmia classification

Taymaz Akan, Sait Alp, Mohammad Alfrad Nobel Bhuiyan

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.LG

AI capabilities can be significantly improved without expensive retraining

Tom Davidson, Jean-Stanislas Denain, Pablo Villalobos, Guillem Bas

专题命中 工具调用 ：tool-use(abstract)；分类 cs.AI、cs.LG

Comments 30 pages, 24 figures

UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities

Hejia Geng, Boxun Xu, Peng Li

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.CL

Reinforcement Learning for Combining Search Methods in the Calibration of Economic ABMs

Aldo Glielmo, Marco Favorito, Debmallya Chanda, Domenico Delli Gatti

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages and 5 figures, presented at the AAAI bridge program 'AI for Financial Institutions' (https://aaai23.bankit.art/), at the ICLR bridge program 'AI4ABM' (https://ai4abm.org/workshop_iclr2023/) and at ICAIF '23 (https://ai-finance.org/). Proceedings of the Fourth ACM International Conference on AI in Finance, (ICAIF 23), Association for Computing Machinery, New York, NY, USA

A Definition of Continual Reinforcement Learning

David Abel, André Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt, Satinder Singh

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2023

Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes

Tao Chen, Megha Tippur, Siyang Wu, Vikash Kumar, Edward Adelson, Pulkit Agrawal

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.LG

Comments Published in Science Robotics: https://www.science.org/doi/10.1126/scirobotics.adc9244

Journal ref Science Robotics, 8(84): eadc9244, 2023

Student of Games: A unified learning algorithm for both perfect and imperfect information games

Martin Schmid, Matej Moravcik, Neil Burch, Rudolf Kadlec, Josh Davidson, Kevin Waugh, Nolan Bard, Finbarr Timbers, Marc Lanctot, G. Zacharias Holland, Elnaz Davoodi, Alden Christianson, Michael Bowling

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in Science Advances

Journal ref Science Advances 9, eadg3256 (2023)

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana, Clément Bonnet, Thomas D. Barrett

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Creating a Discipline-specific Commons for Infectious Disease Epidemiology

Michael M. Wagner, William Hogan, John Levander, Adam Darr, Matt Diller, Max Sibilla, Alexander T. Loiacono. Terence Sperringer,, Shawn T. Brown

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.SE

Comments 12 pages, 6 figures

FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM

Grace Colverd, Paul Darm, Leonard Silverberg, Noah Kasmanoff

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.CL

Comments Version is the one submitted to Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop @Neurips2023. All authors contributed equally to this work

Combining Optimal Path Search With Task-Dependent Learning in a Neural Network

Tomas Kulvicius, Minija Tamosiunaite, Florentin Wörgötter

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 2023

Hedging of Financial Derivative Contracts via Monte Carlo Tree Search

Oleg Szehr

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Corrected typos. Shorter Presentation. 15 pages, 5 figures

Journal ref Journal of Computational Finance, Volume 27, Number 2, Pages: 47-80, 2023

DataComp: In search of the next generation of multimodal datasets

Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt

专题命中 工具调用 ：workflow(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2023 Datasets and Benchmarks Track

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching

H. J. Terry Suh, Glen Chou, Hongkai Dai, Lujie Yang, Abhishek Gupta, Russ Tedrake

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Glen Chou, Hongkai Dai, and Lujie Yang contributed equally to this work. Accepted to CoRL 2023

OpenAgents: An Open Platform for Language Agents in the Wild

Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, Tao Yu

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 34 pages, 8 figures

RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning

Jasmina Gajcin, Ivana Dusparic

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 3 figures, 3 tables

Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned

Brieuc Pinon, Raphaël Jungers, Jean-Charles Delvenne

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG