5 papers
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Zhenhua Xu, Dongsheng Chen, Jian Li +7
Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tun…
Improving Search Agent with One Line of Code
Jian Li, Dongsheng Chen, Zhenhua Xu +5
Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools for a multi-turn information-seeking…
SE-Search: Self-Evolving Search Agent via Memory and Dense Reward
Jian Li, Yizhang Jin, Dongqi Liu +9
Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent se…
Efficient Multimodal Large Language Models: A Survey
Yizhang Jin, Jian Li, Yexin Liu +10
In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning.…
LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description
Yizhang Jin, Jian Li, Jiangning Zhang +7
Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classificatio…