Seth Karten

I am a PhD Candidate in Computer Science at Princeton University advised by Chi Jin. My research develops methods and evaluations for multi-agent systems (zero-sum and general-sum), generalized harnesses for embodied agents, and economic alignment and safety. I study foundation agents that perform closed-loop decision-making in open-ended environments at scale, using complex environments to stress-test fundamentals while enabling rich real-world applications.

✉️ Email 📄 CV 📝 Blog 📚 Google Scholar 💬 SethGPT

GitHub

News

Apr 2026

🎉 GameDevBench has been accepted to ICML 2026.

Mar 2026

🎉 Honored to receive a Tinker Research Grant from Thinking Machines supporting my research on foundation agents.

Feb 2026

🎉 Honored to receive a Google DeepMind research grant supporting my work on generalized harnesses for embodied agents.

Dec 2025

🏆 The PokeAgent Challenge wrapped up with our workshop at NeurIPS 2025, sponsored by Google DeepMind and IJCAI AIJ.

Oct 2025

🎤 I gave a lightning talk on PokéChamp and the PokeAgent Challenge at the 5th Annual Rutgers Robotics Workshop 2025.

Aug 2025

🎤 I gave a lightning talk at UC Berkeley's Agentic AI Summit on PokéChamp and the PokeAgent Challenge.

Jul 2025

⭐ PokéChamp received a Spotlight Award at ICML 2025 and is the first Pokemon battling paper at ICML, ICLR, or NeurIPS.

Jun 2024

🎯 I presented a poster on The LLM Economist: Optimizing Policy in Multiagent Generative Simulations at the Cooperative AI Summer School.

May 2023

🏆 I am excited to announce that I have been awarded Princeton's Francis Robbins Upton Fellowship in Engineering!

Mar 2023

🌟 I am excited to announce that I have been awarded the National Science Foundation Graduate Research Fellowship (NSF GRFP)!

Selected Publications

Economic Alignment

LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

Seth Karten, Wenzhe Li, Zihan Ding, Samuel Kleiner, Yu Bai, Chi Jin

NeurIPS Algorithmic Collective Action Workshop, 2025

Abstract PDF Code

Agent Harnesses

PokéChamp: An Expert-level Minimax Language Agent

Seth Karten, Andy Nguyen, Chi Jin

ICML (Spotlight), 2025

Abstract PDF Code Website

Evaluations & RL Environments

The PokeAgent Challenge: Competitive and Long Context Learning at Scale

Seth Karten, Jake Grigsby, Stephanie Milani, Kiran Vodrahalli, Amy Zhang, Fei Fang, Yuke Zhu, Chi Jin

NeurIPS Competition Track, 2025

Abstract PDF Website

GameDevBench: Evaluating Agentic Capabilities Through Game Development

Wayne Chi, Yixiong Fang, Arnav Yayavaram, Siddharth Yayavaram, Seth Karten, Qiuhong Anna Wei, Runkun Chen, Alexander Wang, Valerie Chen, Ameet Talwalkar, Chris Donahue

ICML, 2026

Abstract PDF

Automatic Generation of High-Performance RL Environments

Seth Karten, Rahul Dev Appapogu, Chi Jin

arXiv preprint, 2026

Abstract PDF

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

Wenzhe Li, Zihan Ding, Seth Karten, Chi Jin

ICML, 2024

Abstract PDF Code

Emergent Communication

On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning

Seth Karten, Siva Kailas, Huao Li, Katia Sycara

AAMAS, 2023

Abstract PDF Code

Towards True Lossless Sparse Communication in Multi-Agent Systems

Seth Karten, Mycal Tucker, Siva Kailas, Katia Sycara

ICRA, 2023

Abstract PDF Code

Interpretable Learned Emergent Communication for Human-Agent Teams

Seth Karten, Mycal Tucker, Huao Li, Siva Kailas, Michael Lewis, Katia Sycara

IEEE Transactions on Cognitive and Developmental Systems, 2023

PDF Code

Robotics

Improving Kinodynamic Planners for Vehicular Navigation with Learned Goal-Reaching Controllers

Aravind Sivaramakrishnan, Edgar Granados, Seth Karten, Troy McMahon, Kostas E. Bekris

IROS, 2021

PDF

A complete paper index with metadata, abstracts, and BibTeX is available on Research. A lightweight machine-readable guide is also available at llms.txt.

📖 Background

🎯 Opportunities