Towards General Agentic Intelligence via Environment Scaling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Runnan, Cai, Shihao, Li, Baixuan, Wu, Jialong, Li, Guangyu, Yin, Wenbiao, Wang, Xinyu, Wang, Xiaobin, Su, Liangcai, Zhang, Zhen, Wu, Shibin, Tao, Zhengwei, Jiang, Yong, Xie, Pengjun, Huang, Fei, Zhou, Jingren
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911157998059520
author Fang, Runnan
Cai, Shihao
Li, Baixuan
Wu, Jialong
Li, Guangyu
Yin, Wenbiao
Wang, Xinyu
Wang, Xiaobin
Su, Liangcai
Zhang, Zhen
Wu, Shibin
Tao, Zhengwei
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
author_facet Fang, Runnan
Cai, Shihao
Li, Baixuan
Wu, Jialong
Li, Guangyu
Yin, Wenbiao
Wang, Xinyu
Wang, Xiaobin
Su, Liangcai
Zhang, Zhen
Wu, Shibin
Tao, Zhengwei
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
contents Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards General Agentic Intelligence via Environment Scaling
Fang, Runnan
Cai, Shihao
Li, Baixuan
Wu, Jialong
Li, Guangyu
Yin, Wenbiao
Wang, Xinyu
Wang, Xiaobin
Su, Liangcai
Zhang, Zhen
Wu, Shibin
Tao, Zhengwei
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
Computation and Language
Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.
title Towards General Agentic Intelligence via Environment Scaling
topic Computation and Language
url https://arxiv.org/abs/2509.13311