RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Abstract
An end-to-end reinforcement learning framework using simulated user emotion rewards enhances emotional intelligence in large language models while maintaining cognitive skills.
Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other domains, its application to dialogue-especially for emotional intelligence-remains underexplored. In this work, we introduce RLVER, the first end-to-end reinforcement learning framework that leverages verifiable emotion rewards from simulated users to cultivate higher-order empathetic abilities in LLMs. Within this framework, self-consistent affective simulated users engage in dialogue rollouts and produce deterministic emotion scores during conversations, serving as reward signals to guide the LLM's learning. Fine-tuning publicly available Qwen2.5-7B-Instruct model with PPO boosts its Sentient-Benchmark score from 13.3 to 79.2 while largely preserving mathematical and coding competence. Extensive experiments reveal that: (i) RLVER consistently improves multiple dialogue capabilities; (ii) Thinking and non-thinking models show distinct trends--thinking models excel in empathy and insight, while non-thinking models favor action; (iii) GRPO often yields stable gains, while PPO can push certain capabilities to a higher ceiling; (iv) More challenging environments are not always better-moderate ones can yield stronger outcomes. Our results show that RLVER is a practical route toward emotionally intelligent and broadly capable language agents.
Community
This paper introduces the first RLVR framework to boost LLM empathy, using a simulated user that turns emotional reactions into reward signals with open-sourcing code, checkpoints, and scripts to accelerate research into emotionally intelligent AI.
Check out the code ๐:
https://github.com/Tencent/DigitalHuman/tree/main/RLVER
Join the conversation on Twitter ๐ฌ:
https://x.com/tuzhaopeng/status/1940963412848398449
Models citing this paper 4
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper