5 papers
Understanding Communication Failures in Multi-Agent LLM Systems
Priya Pitre, Jun Hou, Yi Fang +2
Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy alone cann…
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
Jun Hou, Priya Pitre, Yi Fang +1
Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, ste…
Agentic Framework for Epidemiological Modeling
Rituparna Datta, Zihan Guan, Baltazar Espinoza +5
Epidemic modeling is essential for public health planning, yet traditional approaches rely on fixed model classes that require manual redesign as pathogens, policies, and scenario…
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi +5
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce…
ArguMentor: Augmenting User Experiences with Counter-Perspectives
Priya Pitre, Kurt Luther
We encounter arguments everyday in the form of social media posts, presidential debates, news articles, and even advertisements. A ubiquitous, influential example is the opinion pi…