44 citations · 110 across the 37 of their papers we have counts for
9 papers · 1 filter
What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds
Caixin Kang, Ke Wang, Yuchuan Wu +5
Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of social agents…
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
Yuchuan Wu, Ke Niu, Haiyang Yu +3
Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, procedural reasoning, and precise…
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
Yuchuan Wu, Xuan Luo, Yinglian Zhu +3
Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, singl…
EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management
Rongzhi Zhu, Xiang Huang, Yuchuan Wu +8
Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation. However, emotion managemen…
Scaling Self-Evolving Agents via Parametric Memory
Tao Ren, Weiyao Luo, Hui Yang +8
Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout…
AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
Yuchuan Wu, Yinglian Zhu, Haiyang Yu +3
Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are…
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
Yuchuan Wu, Minghan Zhuo, Teng Fu +3
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes sc…
P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
Pinyi Zhang, Ting-En Lin, Yuchuan Wu +7
Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key challenge is obtaining accurate…
Reward Modeling from Natural Language Human Feedback
Zongqi Wang, Rui Wang, Yuchuan Wu +5
Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewar…