PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
Quick Answer
PathoSage introduces a three-stage framework for patch-level pathology reasoning, effectively reducing hallucinations and classifier disagreement.
Quick Take
Its Structured Evidence Deliberation component enhances decision-making by evaluating heterogeneous evidence and mitigating anchoring bias, outperforming existing MLLM and agentic systems in experiments.
Key Points
- PathoSage separates knowledge retrieval, evidence collection, and adjudication for improved reasoning.
- Structured Evidence Deliberation independently evaluates evidence, reducing anchoring bias.
- The framework outperforms existing MLLM and agentic baselines in experiments.
- Introduces a training-free Beta-Bernoulli experience system for tool reliability.
- Mitigates hallucinations in visual question answering (VQA) tasks.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 07549v1 Announce Type: new Abstract: Recent advances in Multimodal (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patch-level reasoning remains challenging. End-to-end pathology MLLMs often hallucinate morphological features, while recent agentic systems usually merge tool outputs and retrieved knowledge into a shared context, making decisions vulnerable to conflicting evidence and context contamination.
We propose PathoSage, a three-stage framework that explicitly separates knowledge retrieval, evidence collection, and evidence adjudication for patch-level pathology multimodal reasoning. Its core component, Structured Evidence Deliberation, independently evaluates heterogeneous evidence from tools, performs conflict analysis, and generates the final judgment in a fresh context to reduce anchoring bias.
We further introduce a training-free Beta-Bernoulli experience system with continuous credit assignment to model long-term tool reliability and construct similarity-weighted priors for future . Experiments show that PathoSage effectively mitigates VQA hallucinations and classifier disagreement, outperforming strong pathology MLLM and agentic baselines. Our results highlight explicit evidence adjudication and reliability-aware tool modeling as key ingredients for robust pathology agents.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.