3 papers
cs.AI2025
Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents
Wenda Xie, Chao Guo, Yanqing Jing +3
Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and…
cs.LG2025
Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting
Yueyang Yao, Jiajun Li, Xingyuan Dai +4
Time series forecasting is important for applications spanning energy markets, climate analysis, and traffic management. However, existing methods struggle to effectively integrate…
cs.AI2025
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Jie Cheng, Gang Xiong, Ruixi Qiao +5
Process reward models (PRMs) have proven effective for test-time scaling of Large Language Models (LLMs) on challenging reasoning tasks. However, reward hacking issues with PRMs li…