Alexey Taymanov — accepted AI-conference papers

2026

WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasks

Hao Bai, Alexey Taymanov, Tong Zhang, Aviral Kumar, Spencer Whitehead

CVPR 2026

We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains nearly 300,000 tasks with rubric-based evaluation

Cited by 0 Source ↗code ↗Scholar ↗

2024

Aligning LLM Agents by Learning Latent Preference from User Edits

Ge Gao, Alexey Taymanov, Eduardo Salinas, Paul Mineiro, Dipendra Misra

NeurIPS 2024poster

We study interactive learning of language agents based on user edits made to the agent's output. In a typical setting such as writing assistants, the user interacts with a language agent to generate a response given a context, and may optionally edit the agent response to personalize it based on the…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗