Research
PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
Researchers propose a new framework for AI pathology diagnosis that separates knowledge retrieval from evidence evaluation to reduce hallucinations. The system includes a novel experience-tracking mechanism to assess tool reliability over time, addressing critical accuracy concerns in medical AI applications.
Read full story at cs.AI updates on arXiv.org →V:0.3 · A:0.3 · D:0.4
Related
Research
Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
Researchers introduce Pythagoras-Prover, a compute-efficient family of Lean theorem provers that achieves strong perform...
Research
Can AI Agents Synthesize Scientific Conclusions?
Researchers created SciConBench, a benchmark testing AI agents' ability to synthesize scientific conclusions from multip...
Research
How memory tools can make AI models worse
New research suggests that AI memory systems intended to improve model performance can actually degrade capabilities and...