Towards General Agentic Intelligence via Environment Scaling

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin WU, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Ningyu Zhang, Wentao Zhang, Jingren Zhou

Keywords: tool use, general agent

Abstract:

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 inter-
actions with these environments. To address these, we design a scalable frame-
work 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, τ-bench,
τ2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler,
significantly enhances the models’ function-calling capability.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 10286