6 papers
TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
Suizhi Huang, Mei Li, Han Yu +1
Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause o…
AI as We Describe It: How Large Language Models and Their Applications in Health are Represented Across Channels of Public Discourse
Jiawei Zhou, Lei Zhang, Mei Li +2
Representation shapes public attitudes and behaviors. With the recent advances and rapid adoption of LLMs, the way these systems are introduced will negotiate societal expectations…
OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models
Shiyuan Li, Yixin Liu, Yu Zheng +3
Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems, yet their performance is critically dependent on the design of their underlying collaboration topo…
Understanding Down Syndrome Stereotypes in LLM-Based Personas
Chantelle Wu, Peinan Wang, Nafi Nibras +6
We present a case study of Persona-L, a system that leverages large language models (LLMs) and retrieval-augmented generation (RAG) to model personas of people with Down syndrome.…
A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
Jiale Guo, Suizhi Huang, Mei Li +8
The integration of Large Language Models (LLMs) into software engineering has driven a transition from traditional rule-based systems to autonomous agentic systems capable of solvi…
SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
Tianhao Li, Jingyu Lu, Chuangxin Chu +12
Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring…