# Evaluating Agentic Harness Systems for Autonomous Computational Pathology

arXiv: https://arxiv.org/abs/2607.02598 · HTML: https://mlsanity.com/paper/2607.02598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 17 of 17)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [A co-evolving agentic AI system for medical imaging analysis](https://mlsanity.com/paper/2509.20279/) (2025)
- [MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization](https://mlsanity.com/paper/2604.21937/) (2026)
- [NOVA: An Agentic Framework for Automated Histopathology Analysis and Discovery](https://mlsanity.com/paper/2511.11324/) (2025)

## Abstract (arXiv)

Autonomous computational pathology (ACP) converts high-level pathology analysis goals into executable, traceable and clinically bounded workflows. Realizing this capability requires adapting general agentic harness systems to pathology-specific tasks, tools, evidence standards and clinical claim boundaries. We contribute ACP-Bench, a framework that adapts existing harness systems from computational pathology support toward ACP workflow capability. ACP-Bench evaluates 41 pathology workflow tasks, including 24 biomarker, 7 morphology and 10 prognosis tasks spanning 6 body-system groups and 9 endpoint families. The benchmark evaluates 9 models and 3 harness groups (Claude Code, Codex and Open Code), yielding 369 complete trajectories. ACP-Bench evaluates each trajectory across workflow execution, diagnostic performance and clinical-boundary alignment, combining expert-adjudicated process audits, diagnostic assessment and pathologist-validated safety review. Across evaluated systems, workflow initiation, task interpretation and diagnostic reporting were more mature than tool-bound execution, result binding and reflective workflow revision, and formal end-to-end completion remained rare. ACP-Bench provides a reusable standard for auditing whether agentic systems can operationalize pathology workflows before claims of reliable clinical autonomy.