Epistemic Exploration Toward Artificial General Intelligence
Authors/Creators
- Ban, Yikun
- Yang, Fengkai
- Chen, Fangzheng
- Wang, Yibo
- Chen, Zhijun
- Li, Zhongyi
- Huang, Zixuan
- Zhang, Xiaoyuan
- Li, Gongxun
- Chen, Zehao
- Wang, Huaiyang
- Lu, Xiaodong
- Yang, Yaocheng
- Wei, Pengcheng
- Tian, Wan
- Chen, Zherui
- Zhang, Zhixia
- Xie, Hongyan
- Lv, Lingyu
- Wang, Xiaohan
- Chai, Jiajun
- Yin, Guojun
- Lin, Wei
- Ai, Tianxiang
- Wang, Ruijie
- Zhou, Haoyi
- Lu, Chaochao
- Che, Wanxiang
- Zhuang, Fuzhen
- Ding, Ning
- Xu, Qianqian
- Wang, Deqing
- Yang, Yaodong
- Li, Jianxin
Description
Exploration is not an optional behavior in natural intelligence; it is an evolutionary principle underlying the emergence and adaptation of intelligence. Curiosity, play, and deliberate probing emerge as evolved responses to uncertainty, enabling organisms to construct internal models, expand competence, and preserve adaptability in changing environments. We argue that this evolutionary logic is equally indispensable for artificial general intelligence (AGI): exploration is not a heuristic appended to learning, but the mechanism through which generality becomes possible. We develop a unified view of Epistemic Exploration: the capacity of an agent to actively acquire information that reduces uncertainty about the world, seek experiences at the boundary of its current capabilities and convert them into durable capability improvement, and preserve epistemic reachability as the readiness and ability to adapt when the world changes. This view yields three criteria: Information Gain, Value Improvement, and Epistemic Reachability. We then introduce an exploration-centered five-level trajectory toward AGI, in which each level is characterised by a distinct exploration capacity, and exploration serves as the transition mechanism among levels:
-
Responder: minimal or no explicit epistemic exploration; the system mainly relies on learned input–output mappings and local token-level variation.
-
Reasoner: reasoning-space exploration enables hypothesis search, deliberate reasoning trajectories, branching, backtracking, and self-verification beyond reactive response generation.
-
Agent: interaction-space exploration extends internal deliberation into embodied perception, tool use, memory, and closed-loop action under partial observability.
-
Prospector: imagination-space exploration uses learned world models to simulate counterfactual futures, reduce the cost and risk of real interaction, and support long-horizon policy improvement.
-
Ecosystem: coordination-space exploration enables collectives of heterogeneous agents to co-evolve roles, shared representations, communications, and collaborative strategies beyond the limits of any single agent.
Finally, we conclude with evaluation principles and open challenges for building exploration-centric agents that continually reduce uncertainty, improve their own capabilities, and maintain readiness to adapt beyond predefined tasks.
Files
Epistemic Exploration Toward Artificial General Intelligence.pdf
Files
(7.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:4c39e67be1616a4a2dcb075cd2f3b6d7
|
7.1 MB | Preview Download |