6 papers
FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
Zhixin Han, Yanzhi Zhang, Chuyang Wei +11
Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using large language model-based agent…
The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
Ruihan Yang, Fanghua Ye, Jian Li +5
Large language models (LLMs) have recently transformed from text-based assistants to autonomous agents capable of planning, reasoning, and iteratively improving their actions. Whil…
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
Cheng Liu, Yifei Lu, Fanghua Ye +5
Role-Playing Language Agents (RPLAs) have emerged as a significant application direction for Large Language Models (LLMs). Existing approaches typically rely on prompt engineering…
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Peisong Wang, Ruotian Ma, Bang Zhang +13
Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement le…
CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
Yifei Lu, Fanghua Ye, Jian Li +6
Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as in…
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
Bang Zhang, Ruotian Ma, Qingxuan Jiang +10
Assessing how well a large language model (LLM) understands human, rather than merely text, remains an open challenge. To bridge the gap, we introduce Sentient Agent as a Judge (SA…