# LongHarness tests evidence management for long-context agents

> The framework supports agent answers by updating evidence and conclusions together across long documents.

- Canonical URL: https://newsverum.com/en/news/longharness-tests-evidence-management-for-long-context-agents
- Publisher: Newsverum
- Section: Technology
- Country: China
- Published: 2026-10-13T00:51:40+00:00
- Updated: 2026-10-13T00:51:40+00:00
- Event / data period: 2026-10-09
- Other editions: [Türkçe](https://newsverum.com/tr/news/longharness-tests-evidence-management-for-long-context-agents.md), [العربية](https://newsverum.com/ar/news/longharness-tests-evidence-management-for-long-context-agents.md), [Français](https://newsverum.com/fr/news/longharness-tests-evidence-management-for-long-context-agents.md), [Español](https://newsverum.com/es/news/longharness-tests-evidence-management-for-long-context-agents.md), [Deutsch](https://newsverum.com/de/news/longharness-tests-evidence-management-for-long-context-agents.md), [Português](https://newsverum.com/pt/news/longharness-tests-evidence-management-for-long-context-agents.md)

Researchers affiliated with Fudan University, Shanghai AI Laboratory and Peking University in China introduced LongHarness. The system manages source-linked evidence across long document collections; as new evidence arrives, it updates both the evidence pool and provisional conclusions.

In the evaluation on the first version of OfficeQA Pro, the paper reports a 60.2% exact-match rate with GLM-5.3-Flash. The authors describe a substantial increase over direct model use, but the result is limited to the constructed benchmark and the tested model and retrieval setup. It does not establish the same performance in every real long-context workflow.

## Data

### Research result

OfficeQA Pro V1; benchmark of about 100 million tokens; exact match

Methodology: The value is limited to the benchmark experiment reported in the paper; it is not a field result or general performance guarantee.

| Measure | Percent | Scope |
|---|---|---|
| GLM-5.3-Flash exact-match rate on OfficeQA Pro V1 | 60.2 | OfficeQA Pro V1; benchmark of about 100 million tokens; exact match |

Sources: <https://arxiv.org/html/2610.13075v1> · Download data: [JSON](https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents/data/reported-result-1?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents/data/reported-result-1?lang=en&format=csv)

## Sources

- [arXiv preprint by researchers affiliated with Fudan University, Shanghai AI Laboratory, Peking University and other Chinese institutions](<https://arxiv.org/html/2610.13075v1>) (Source checked: 2026-10-13; Published: 2026-10-09)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)