2 papers
cs.CL2026
Mint-Agent: Introducing Finance-Native Agentic Foundation Models
Agent Team, B. Zhang, Gavin Zhang +8
Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon…
cs.CL2026
HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals
Zhihao Guo, Zonghan Wu, Huan Huo +6
Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments. These models n…