NJ
Natasha Jaques
cs.AIcs.LGcs.CLcs.MAstat.MLcs.CYAlgorithmscs.CRcs.CVcs.HC
On Valency
published · living versionsW_3sasu23e·v1 · currentpublished
s: Simple Scaling of Swarms via Cooperative Multi-agent RL
with Kunal Jha, Gonçalo Faria, Shuyue Stella Li, Scott Geng +4
1 version
W_gjgnbpx9·v1published
Preprints & journals
73 papers in the corpus · 2015–2026AutoEnvScaling: Automating the Data Flywheel with Terminal Agents2610.14163v1 · Simon Yu, Baolin Peng, Bo Liu et al.2026 · 0 citationsarXiv
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks2610.05346v1 · Emanuele La Malfa, Saar Cohen, Gabriele La Malfa et al.2026 · 0 citationsarXiv
Mitigating Social Sycophancy via Pluralistic Preference Optimization2610.02568v2 · Stephane Hatgis-Kessell, Myra Cheng, Xiaoxuan Hou et al.2026 · 0 citationsarXiv
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs2609.38516v2 · Kunal Jha, Max Kleiman-Weiner, Natasha Jaques2026 · 0 citationsarXiv
Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning2609.14896v1 · Jiayi Yuan, Hangoo Kang, James Jihao Liu et al.2026 · 0 citationsarXiv
Tapes Together Strong: The Co-evolution of Computation and Cooperation2609.10817v1 · Kunal Jha, Francesco Cicala, Blaise Aguera y Arcas et al.2026 · 0 citationsarXiv
Demystifying Reinforcement Learning Post-Training of Language Models2608.24949v2 · Donovan Clay, Saket Gollapudi, Sankar Harilal et al.2026 · 0 citationsarXiv
SPADE: Self-Play in Adaptive Synthetic Executable Environments2608.19197v3 · Bo Liu, Simon Yu, Yiding Jiang et al.2026 · 0 citationsarXiv
Debate Training Reduces Reward Hacking in RLAIF2608.17776v1 · Zachary Kenton, Lili Janzer, Rory Greig et al.2026 · 0 citationsarXiv
Pigeonholing: how bad prompts hurt models, causing collapse and mistakes2606.24267v3 · Hyunji Nam, Keertana Chidambaram, Dorottya Demszky et al.2026 · 0 citationsarXiv
Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents2606.18537v2 · Caleb Chang, Davin Win Kyi, Natasha Jaques et al.2026 · 0 citationsarXiv
Learn to Match: Two-Sided Matching with Temporally Extended Feedback2606.06744v2 · Haijing Zong, Yancheng Liang, Boyang Zhou et al.2026 · 0 citationsarXiv
Solipsistic Superintelligence is Unlikely to be Cooperative2606.03237v1 · Rakshit S Trivedi, Natasha Jaques, Logan Cross et al.2026 · 0 citationsarXiv
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents2605.12894v3 · Harshita Chopra, Kshitish Ghate, Aylin Caliskan et al.2026 · 0 citationsarXiv
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems2605.11514v1 · Fanxiao Li, Jiaying Wu, Tingchao Fu et al.2026 · 0 citationsarXiv
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning2604.14140v1 · Sumeet Ramesh Motwani, Daniel Nichols, Charles London et al.2026 · 0 citationsarXiv
How LLMs Distort Our Written Language2603.18161v2 · Marwa Abdulhai, Isadora White, Yanming Wan et al.2026 · 2 citationsarXiv
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data2603.19294v6 · Hyunji Nam, Haoran Li, Natasha Jaques2026 · 0 citationsarXiv
Improving Interactive In-Context Learning from Natural Language Feedback2602.16066v1 · Martin Klissarov, Jonathan Cook, Diego Antognini et al.2026 · 0 citationsarXiv
Are Language Models Sensitive to Morally Irrelevant Distractors?2602.09416v2 · Andrew Shaw, Christina Hahn, Catherine Rasgaitis et al.2026 · 0 citationsarXiv
AgenticRed: Evolving Agentic Systems for Red-Teaming2601.13518v3 · Jiayi Yuan, Jonathan Nother, Natasha Jaques et al.2026 · 0 citationsarXiv
Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia2512.03318v1 · Chandler Smith, Marwa Abdulhai, Manfred Diaz et al.2025 · 0 citationsarXiv
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction2511.17879v4 · Yusong Wu, Stephen Brade, Aleksandra Teng Ma et al.2025 · 0 citationsarXiv
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments2511.07317v2 · Zhiyuan Zeng, Hamish Ivison, Yiping Wang et al.2025 · 0 citationsarXiv
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning2511.00222v1 · Marwa Abdulhai, Ryan Cheng, Donovan Clay et al.2025 · 2 citationsarXiv
Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL2510.14318v1 · Marwa Abdulhai, Ryan Cheng, Aryansh Shrivastava et al.2025 · 0 citationsarXiv
Modeling Others' Minds as Code2510.01272v1 · Kunal Jha, Aydan Yuenan Huang, Eric Ye et al.2025 · 0 citationsarXiv
AutoCode: LLMs as Problem Setters for Competitive Programming2510.12803v1 · Shang Zhou, Zihan Zheng, Kaiyuan Liu et al.2025 · 0 citationsarXiv
An Efficient Open World Environment for Multi-Agent Social Learning2508.15679v1 · Eric Ye, Ren Tao, Natasha Jaques2025 · 0 citationsarXiv
Generative Modeling for Robust Deep Reinforcement Learning on the Traveling Salesman Problem2508.08718v1 · Michael Li, Eric Bae, Christopher Haberland et al.2025 · 0 citationsarXiv
Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping2507.16249v1 · Srivatsan Krishnan, Jason Jabbour, Dan Zhang et al.2025 · 0 citationsarXiv
Learning to summarize user information for personalized reinforcement learning from human feedback2507.13579v4 · Hyunji Nam, Yanming Wan, Mickel Liu et al.2025 · 0 citationsarXiv
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning2506.24119v3 · Bo Liu, Leon Guertler, Simon Yu et al.2025 · 0 citationsarXiv
Adaptive Accompaniment with ReaLchords2506.14723v1 · Yusong Wu, Tim Cooijmans, Kyle Kastner et al.2025 · 0 citationsarXiv
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models2506.07468v4 · Mickel Liu, Liwei Jiang, Yancheng Liang et al.2025 · 0 citationsarXiv
Improving Human-AI Coordination through Online Adversarial Training and Generative Models2504.15457v4 · Paresh Chaudhary, Yancheng Liang, Daphne Chen et al.2025 · 0 citationsarXiv
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination2504.12714v2 · Kunal Jha, Wilka Carvalho, Yancheng Liang et al.2025 · 0 citationsarXiv
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward2504.03206v3 · Yanming Wan, Jiaxing Wu, Marwa Abdulhai et al.2025 · 2 citationsarXiv
ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned Transformers2502.21267v1 · Alexander Scarlatos, Yusong Wu, Ian Simon et al.2025 · 5 citationsarXiv
Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems2412.15573v1 · Joshua Holder, Natasha Jaques, Mehran Mesbahi2024 · 5 citationsarXiv
Learning to Cooperate with Humans using Generative Agents2411.13934v1 · Yancheng Liang, Daphne Chen, Abhishek Gupta et al.2024 · 3 citationsarXiv
InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma2411.09856v3 · Xiaoxuan Hou, Jiayi Yuan, Joel Z. Leibo et al.2024 · 0 citationsarXiv
Infer Human's Intentions Before Following Natural Language Instructions2409.18073v2 · Yanming Wan, Yue Wu, Yiping Wang et al.2024 · 1 citationarXiv
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning2408.10075v1 · Sriyash Poddar, Yanming Wan, Hamish Ivison et al.2024 · 12 citationsarXiv
Achieving Human Level Competitive Robot Table Tennis2408.03906v3 · David B. D'Ambrosio, Saminda Abeyruwan, Laura Graesser et al.2024 · 9 citationsarXiv
Impossibility theorems for feature attribution.38181057 · Bilodeau, Blair, Jaques, Natasha, Koh, Pang Wei et al.2024 · 108 citationsProceedings of the National Academy of Sciences of the United States of America. 2024;121(2):e2304406120
Moral Foundations of Large Language Models2310.15337v1 · Marwa Abdulhai, Gregory Serapio-Garcia, Cl'ement Crepy et al.2023 · 44 citationsarXiv
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration2211.16385v1 · Srivatsan Krishnan, Natasha Jaques, Shayegan Omidshafiei et al.2022 · 3 citationsarXiv
Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience2208.04919v1 · Marwa Abdulhai, Natasha Jaques, Sergey Levine2022 · 2 citationsarXiv
Wearables: An R Package With Accompanying Shiny Application for Signal Analysis of a Wearable Device Targeted at Clinicians and Researchers.35813597 · de Looff, Peter, Duursma, Remko, Noordzij, Matthijs et al.2022 · 19 citationsFrontiers in behavioral neuroscience. 2022;16:856544
Career total: 104 works. 73 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.