Showing 2026Show all
3 papers · 1 filter
cs.AI2026
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
Jieyi Wang, Bingxuan Li, Nanyi Jiang +9
Biomedical deep-research systems increasingly retrieve and synthesize scientific evidence, but their outputs typically collapse heterogeneous evidence into static text, making prov…
cs.AI2026
Bayesian and Motivated Reasoning in AI Agents
Eddie Yang
AI agents increasingly perform open-ended tasks in settings where their conclusions can guide consequential decisions. We provide evidence that AI agents draw different conclusions…
cs.CL2026
Benchmark Illusion: Disagreement among LLMs and Its Scientific Consequences
Eddie Yang, Dashun Wang
Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep e…