KARL: Knowledge Agents via Reinforcement Learning.

Alexander Trott Alexander R. Trott Alex Trott

Jonathan D. Chang Andrew Drozdov Shubham Toshniwal Owen Oertell Alexander Trott Jacob P. Portes Abhay Gupta Pallavi Koppol Ashutosh Baheti Sean Kulinski Ivan Zhou Irene Dea Krista Opsahl-Ong Simon Favreau-Lessard Sean Owen Jose Javier Gonzalez Ortiz Arnav Singhvi Xabi Andrade Cindy Wang Kartik Sreenivasan Sam Havens Jialu Liu Peyton DeNiro Wen Sun 0002 Michael Bendersky Jonathan Frankle KARL: Knowledge Agents via Reinforcement Learning. 2026 March abs/2603.05218 CoRR https://doi.org/10.48550/arXiv.2603.05218 db/journals/corr/corr2603.html#abs-2603-05218 streams/journals/corr

Eric Zhao 0003 Alexander R. Trott Caiming Xiong Stephan Zheng Learning to Play General-Sum Games against Multiple Boundedly Rational Agents. 11781-11789 2023 AAAI https://doi.org/10.1609/aaai.v37i10.26391 conf/aaai/2023 db/conf/aaai/aaai2023.html#0003TXZ23 Michael Curry 0002 Alexander Trott Soham Phade Yu Bai Stephan Zheng Learning Solutions in Large Economic Networks using Deep Multi-Agent Reinforcement Learning. 2760-2762 2023 AAMAS https://dl.acm.org/doi/10.5555/3545946.3599069 conf/atal/2023 db/conf/atal/aamas2023.html#CurryTPBZ23 Jacob P. Portes Alexander Trott Sam Havens Daniel King Abhinav Venigalla Moin Nadeem Nikhil Sardana Daya Khudia Jonathan Frankle MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/095a6917768712b7ccc61acbeecad1d8-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#PortesTHKVNSKF23 Xintong Wang 0002 Gary Qiurui Ma Alon Eden Clara Li Alexander Trott Stephan Zheng David C. Parkes Platform Behavior under Market Shocks: A Simulation Framework and Reinforcement-Learning Based Study. 3592-3602 2023 WWW https://doi.org/10.1145/3543507.3583523 conf/www/2023 db/conf/www/www2023.html#WangMELTZP23

Aditi Jha Sam Havens Jeremy Dohmann Alex Trott Jacob P. Portes LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms. 2023 abs/2311.13133 CoRR https://doi.org/10.48550/arXiv.2311.13133 db/journals/corr/corr2311.html#abs-2311-13133

Jacob P. Portes Alex Trott Sam Havens Daniel King Abhinav Venigalla Moin Nadeem Nikhil Sardana Daya Khudia Jonathan Frankle MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining. 2023 abs/2312.17482 CoRR https://doi.org/10.48550/arXiv.2312.17482 db/journals/corr/corr2312.html#abs-2312-17482

Tong Mu Stephan Zheng Alexander R. Trott Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning. 2022 2022 Trans. Mach. Learn. Res. https://openreview.net/forum?id=DY1pMrmDkm db/journals/tmlr/tmlr2022.html#MuZT22

Michael Curry 0002 Alexander Trott Soham Phade Yu Bai Stephan Zheng Finding General Equilibria in Many-Agent Economic Simulations Using Deep Reinforcement Learning. 2022 abs/2201.01163 CoRR https://arxiv.org/abs/2201.01163 db/journals/corr/corr2201.html#abs-2201-01163

Tong Mu Stephan Zheng Alexander Trott Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principal. 2022 abs/2202.01691 CoRR https://arxiv.org/abs/2202.01691 db/journals/corr/corr2202.html#abs-2202-01691

Xintong Wang 0002 Gary Qiurui Ma Alon Eden Clara Li Alexander Trott Stephan Zheng David C. Parkes Using Reinforcement Learning to Study Platform Economies under Market Shocks. 2022 abs/2203.13395 CoRR https://doi.org/10.48550/arXiv.2203.13395 db/journals/corr/corr2203.html#abs-2203-13395

Eric Zhao 0003 Alexander R. Trott Caiming Xiong Stephan Zheng ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in Multi-Agent Simulations. 2021 abs/2106.05492 CoRR https://arxiv.org/abs/2106.05492 db/journals/corr/corr2106.html#abs-2106-05492

Stephan Zheng Alexander Trott Sunil Srinivasa David C. Parkes Richard Socher The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning. 2021 abs/2108.02755 CoRR https://arxiv.org/abs/2108.02755 db/journals/corr/corr2108.html#abs-2108-02755

Alexander Trott Sunil Srinivasa Douwe van der Wal Sebastien Haneuse Stephan Zheng Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist. 2021 abs/2108.02904 CoRR https://arxiv.org/abs/2108.02904 db/journals/corr/corr2108.html#abs-2108-02904

Victor Campos 0001 Alexander Trott Caiming Xiong Richard Socher Xavier Giró-i-Nieto Jordi Torres Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills. 1317-1327 2020 ICML http://proceedings.mlr.press/v119/campos20a.html conf/icml/2020 db/conf/icml/icml2020.html#CamposTXSGT20

Víctor Campos 0001 Alexander Trott Caiming Xiong Richard Socher Xavier Giró-i-Nieto Jordi Torres Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills. 2020 abs/2002.03647 CoRR https://arxiv.org/abs/2002.03647 db/journals/corr/corr2002.html#abs-2002-03647

Stephan Zheng Alexander Trott Sunil Srinivasa Nikhil Naik 0002 Melvin Gruesbeck David C. Parkes Richard Socher The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies. 2020 abs/2004.13332 CoRR https://arxiv.org/abs/2004.13332 db/journals/corr/corr2004.html#abs-2004-13332

Hao Liu Alexander Trott Richard Socher Caiming Xiong Competitive experience replay. 2019 ICLR (Poster) https://openreview.net/forum?id=Sklsm20ctX conf/iclr/2019 db/conf/iclr/iclr2019.html#LiuTSX19 Alexander Trott Stephan Zheng Caiming Xiong Richard Socher Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards. 10376-10386 2019 NeurIPS https://proceedings.neurips.cc/paper/2019/hash/64c26b2a2dcf068c49894bd07e0e6389-Abstract.html http://papers.nips.cc/paper/9225-keeping-your-distance-solving-sparse-reward-tasks-using-self-balancing-shaped-rewards conf/nips/2019 db/conf/nips/nips2019.html#TrottZXS19

Hao Liu Alexander Trott Richard Socher Caiming Xiong Competitive Experience Replay. 2019 abs/1902.00528 CoRR http://arxiv.org/abs/1902.00528 db/journals/corr/corr1902.html#abs-1902-00528

Wenling Shang Alexander Trott Stephan Zheng Caiming Xiong Richard Socher Learning World Graphs to Accelerate Hierarchical Reinforcement Learning. 2019 abs/1907.00664 CoRR http://arxiv.org/abs/1907.00664 db/journals/corr/corr1907.html#abs-1907-00664

Alexander Trott Stephan Zheng Caiming Xiong Richard Socher Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards. 2019 abs/1911.01417 CoRR http://arxiv.org/abs/1911.01417 db/journals/corr/corr1911.html#abs-1911-01417

Alexander Trott Caiming Xiong Richard Socher Interpretable Counting for Visual Question Answering. 2018 ICLR (Poster) https://openreview.net/forum?id=S1J2ZyZ0Z conf/iclr/2018 db/conf/iclr/iclr2018.html#TrottXS18

Alexander Trott Caiming Xiong Richard Socher Interpretable Counting for Visual Question Answering. 2017 abs/1712.08697 CoRR http://arxiv.org/abs/1712.08697 db/journals/corr/corr1712.html#abs-1712-08697

Xabi Andrade Ashutosh Baheti Yu Bai Michael Bendersky Victor Campos 0001Víctor Campos 0001 Jonathan D. Chang Michael J. CurryMichael Curry 0002 Irene Dea Peyton DeNiro Jeremy Dohmann Andrew Drozdov Alon Eden Simon Favreau-Lessard Jonathan Frankle Xavier Giró-i-Nieto Melvin Gruesbeck Abhay Gupta Sebastien Haneuse Sam Havens Aditi Jha Daya Khudia Daniel King Pallavi Koppol Sean Kulinski Clara Li Hao Liu Jialu Liu Gary Qiurui Ma Tong Mu Moin Nadeem Nikhil Naik 0002 Owen Oertell Krista Opsahl-Ong Jose Javier Gonzalez Ortiz Sean Owen David C. Parkes Soham R. PhadeSoham Phade Jacob P. Portes Nikhil Sardana Wenling Shang Arnav Singhvi Richard Socher Kartik Sreenivasan Sunil Srinivasa Wen Sun 0002 Jordi Torres Shubham Toshniwal Abhinav Venigalla Douwe van der Wal Cindy Wang Xintong Wang 0002 Caiming Xiong Eric Zhao 0003 Stephan Zheng Ivan Zhou