New benchmark tests LLM agents on long-horizon patient advocacy tasks
A new arXiv paper introduces BABA-Bench, which evaluates whether LLM agents helping patients obtain care can both achieve correct outcomes and follow required procedures over long horizons.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-02 05:00 · arXiv cs.AI
BABA-Bench: Evaluating Long-Horizon Patient-Advocacy Agents