Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Naifan, Sun, Ruihan, Su, Ruixi, Ma, Shiqi, Zhang, Shiya, Weng, Xianna, Zhang, Xiaofan, Zhan, Yuhan, Xu, Yuyang, Chen, Zhaohan, Pan, Zhengyuan, Song, Ziyi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.00344
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912737933656064
author Zhang, Naifan
Sun, Ruihan
Su, Ruixi
Ma, Shiqi
Zhang, Shiya
Weng, Xianna
Zhang, Xiaofan
Zhan, Yuhan
Xu, Yuyang
Chen, Zhaohan
Pan, Zhengyuan
Song, Ziyi
author_facet Zhang, Naifan
Sun, Ruihan
Su, Ruixi
Ma, Shiqi
Zhang, Shiya
Weng, Xianna
Zhang, Xiaofan
Zhan, Yuhan
Xu, Yuyang
Chen, Zhaohan
Pan, Zhengyuan
Song, Ziyi
contents The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually defines human intelligence: subjective, emotionally grounded, personality sensitive conversation. This space has often been regarded as inherently subjective and challenging to formalize, making it appear unsuitable for conventional RL pipelines. We show that it is not only possible and it is a solvable and transformative RL problem. We propose the first framework that infers user personality on the fly and optimizes model behavior toward personalized conversational preferences. Contrary to the widespread belief that RL collapses in non-verifiable settings, our method produces consistent, robust, and dramatic improvements in humanlike interaction quality. We also introduce the first dynamic emotional intelligence evaluation suite to quantify these gains. Our model, which is introduced as Echo-N1, behaves far above its base version and outperforming the proprietary Doubao 1.5 Character. This work establishes a new frontier for RL: optimizing models for the deeply subjective, deeply human dimensions of conversation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Echo-N1: Affective RL Frontier
Zhang, Naifan
Sun, Ruihan
Su, Ruixi
Ma, Shiqi
Zhang, Shiya
Weng, Xianna
Zhang, Xiaofan
Zhan, Yuhan
Xu, Yuyang
Chen, Zhaohan
Pan, Zhengyuan
Song, Ziyi
Artificial Intelligence
The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually defines human intelligence: subjective, emotionally grounded, personality sensitive conversation. This space has often been regarded as inherently subjective and challenging to formalize, making it appear unsuitable for conventional RL pipelines. We show that it is not only possible and it is a solvable and transformative RL problem. We propose the first framework that infers user personality on the fly and optimizes model behavior toward personalized conversational preferences. Contrary to the widespread belief that RL collapses in non-verifiable settings, our method produces consistent, robust, and dramatic improvements in humanlike interaction quality. We also introduce the first dynamic emotional intelligence evaluation suite to quantify these gains. Our model, which is introduced as Echo-N1, behaves far above its base version and outperforming the proprietary Doubao 1.5 Character. This work establishes a new frontier for RL: optimizing models for the deeply subjective, deeply human dimensions of conversation.
title Echo-N1: Affective RL Frontier
topic Artificial Intelligence
url https://arxiv.org/abs/2512.00344