collaborators

9 papers

cs.AI2026

Prime Agent: A Self-Improving RLM Harness

Seth Karten, Alex L. Zhang, Kevin Thomas +8

Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-sou…

cs.AI2026

GameDevBench: Evaluating Agentic Capabilities Through Game Development

Wayne Chi, Yixiong Fang, Arnav Yayavaram +8

Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the comple…

cs.LG2026

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

Seth Karten, Cameron Crow, Chi Jin

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to di…

cs.LG2026

Automatic Generation of High-Performance RL Environments

Seth Karten, Rahul Dev Appapogu, Chi Jin

Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specialized engineering. We present a closed…

cs.LG2026

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

Seth Karten, Joel Zhang, Tersoo Upaa +5

Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-obser…

cs.LG2026

Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

Chengshuai Shi, Wenzhe Li, Xinran Liang +10

Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier…