7 papers
MuMuTestUp: Mutation-based Multi-Agent Test Case Update
Dawei Tian, Jiakun Liu, Yun Peng +4
Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, cau…
Deep Pre-Alignment for VLMs
Tianyu Yu, Kechen Fang, Zihao Wan +5
Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffer…
Rethinking Experience Utilization in Self-Evolving Language Model Agents
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +6
Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and upd…
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
On Safety Risks in Experience-Driven Self-Evolving Agents
Weixiang Zhao, Yichen Zhang, Yingshuo Wang +8
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduc…
Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG
Yicheng Zhang, Zhen Qin, Zhaomin Wu +2
Retrieval-augmented generation (RAG) enables large language models (LLMs) to produce evidence-based responses, and its performance hinges on the matching between the retriever and…
Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures
Yicheng Zhang, Zhen Qin, Zhaomin Wu +2
Large language models (LLMs) are increasingly powering web-based applications, whose effectiveness relies on fine-tuning with large-scale instruction data. However, such data often…