Agent Learning via Early Experience

Understand

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks.

• However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use).
• As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to scale and generalizes poorly.
• This limitation stems from the nature of expert demonstrations: they capture only a narrow range of scenarios, and expose the agent to limited environment diversity.