Language Games as the Pathway to Artificial Superhuman Intelligence

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wen, Ying, Wan, Ziyu, Zhang, Shao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913672826191872
author Wen, Ying
Wan, Ziyu
Zhang, Shao
author_facet Wen, Ying
Wan, Ziyu
Zhang, Shao
contents The evolution of large language models (LLMs) toward artificial superhuman intelligence (ASI) hinges on data reproduction, a cyclical process in which models generate, curate and retrain on novel data to refine capabilities. Current methods, however, risk getting stuck in a data reproduction trap: optimizing outputs within fixed human-generated distributions in a closed loop leads to stagnation, as models merely recombine existing knowledge rather than explore new frontiers. In this paper, we propose language games as a pathway to expanded data reproduction, breaking this cycle through three mechanisms: (1) \textit{role fluidity}, which enhances data diversity and coverage by enabling multi-agent systems to dynamically shift roles across tasks; (2) \textit{reward variety}, embedding multiple feedback criteria that can drive complex intelligent behaviors; and (3) \textit{rule plasticity}, iteratively evolving interaction constraints to foster learnability, thereby injecting continual novelty. By scaling language games into global sociotechnical ecosystems, human-AI co-evolution generates unbounded data streams that drive open-ended exploration. This framework redefines data reproduction not as a closed loop but as an engine for superhuman intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Language Games as the Pathway to Artificial Superhuman Intelligence
Wen, Ying
Wan, Ziyu
Zhang, Shao
Artificial Intelligence
Computation and Language
Multiagent Systems
The evolution of large language models (LLMs) toward artificial superhuman intelligence (ASI) hinges on data reproduction, a cyclical process in which models generate, curate and retrain on novel data to refine capabilities. Current methods, however, risk getting stuck in a data reproduction trap: optimizing outputs within fixed human-generated distributions in a closed loop leads to stagnation, as models merely recombine existing knowledge rather than explore new frontiers. In this paper, we propose language games as a pathway to expanded data reproduction, breaking this cycle through three mechanisms: (1) \textit{role fluidity}, which enhances data diversity and coverage by enabling multi-agent systems to dynamically shift roles across tasks; (2) \textit{reward variety}, embedding multiple feedback criteria that can drive complex intelligent behaviors; and (3) \textit{rule plasticity}, iteratively evolving interaction constraints to foster learnability, thereby injecting continual novelty. By scaling language games into global sociotechnical ecosystems, human-AI co-evolution generates unbounded data streams that drive open-ended exploration. This framework redefines data reproduction not as a closed loop but as an engine for superhuman intelligence.
title Language Games as the Pathway to Artificial Superhuman Intelligence
topic Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2501.18924