Can I read Agent Learning via Early Experience on EtoBox?

Agent Learning via Early Experience by Kai Zhang & Xiangchao Chen & Bo Liu & Tianci Xue & Zeyi Liao & Zhihan Liu & Xiyao Wang & Yuting Ning & Zhaorun Chen & Xiaohan Fu & Jian Xie & Yuxuan Sun & Boyu Gou & Qi Qi & Zihang Meng & Jianwei Yang & Ning Zhang & Xian Li & Ashish Shah & Dat Huynh &... is a book available to read on EtoBox.

What is Agent Learning via Early Experience about?

A long-term goal of language agents is to learn and improve through their own experience, ultimatelyoutperforming humans in complex, real-world tasks. However, training agents from experience dataarXiv:2510.08558v1 [cs.AI] 9 Oct 2025with 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 andgeneralizes poorly. This limitation stems from the nature of expert demonstrations: they capture onlya narrow range of scenarios, and expose the agent to limited environment diversity. We address thislimitation with a middle-ground paradigm we call early experience: interaction data generated bythe agent’s own actions, where the resulting future states serve as supervision without reward signals.Within this paradigm we study two strategies of using such data: (1) Implicit world modeling, whichuses collected states to ground the policy in environment dynamics; and (2) Self-reflection, wherethe agent learns from its suboptimal actions to improve reasonin

Author

Kai Zhang & Xiangchao Chen & Bo Liu & Tianci Xue & Zeyi Liao & Zhihan Liu & Xiyao Wang & Yuting Ning & Zhaorun Chen & Xiaohan Fu & Jian Xie & Yuxuan Sun & Boyu Gou & Qi Qi & Zihang Meng & Jianwei Yang & Ning Zhang & Xian Li & Ashish Shah & Dat Huynh &...

Published

2025

Language

EN