4 papers
Reliable agent engineering should integrate machine-compatible organizational principles
R. Patrick Xian, Garry A. Gabison, Ahmed Alaa +2
As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with conce…
Measuring temporal effects of agent knowledge by date-controlled tool use
R. Patrick Xian, Qiming Cui, Stefan Bauer +1
Temporal progression is an integral part of knowledge accumulation and update. Web search is frequently adopted as grounding for agent knowledge, yet an improper configuration affe…
Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
Garry A. Gabison, R. Patrick Xian
Agentic systems powered by large language models (LLMs) are becoming progressively more complex and capable. Their increasing agency and expanding deployment settings attract growi…
Robustness tests for biomedical foundation models should tailor to specifications
R. Patrick Xian, Noah R. Baker, Tom David +5
The rise of biomedical foundation models creates new hurdles in model testing and authorization, given their broad capabilities and susceptibility to complex distribution shifts. W…