5 papers
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning
Xiaolong Wei, Zerun Zhu, Simin Niu +9
A fundamental challenge in creative writing lies in reconciling the inherent tension between maintaining global coherence in long-form narratives and preserving local expressivenes…
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
Hui Wu, Hengyi Cai, Jinman Zhao +6
Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training va…
Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
Xiaolong Wei, Yuehu Dong, Xingliang Wang +5
Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimizat…
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Xiaolong Wei, Bo Lu, Xingyu Zhang +4
Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language…
TURA: Tool-Augmented Unified Retrieval Agent for AI Search
Zhejun Zhao, Yuchen Li, Alley Liu +8
The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpor…