benchmark · first seen 8 Oct 2026
agent harness evaluation
Also: agent measurement, agent harness evals, harness benchmarking
Evaluation of the scaffolding or harness code wrapping language models in agent systems.
Mentions per week
PapersCodeDiscussion
Earliest sources
- zjunlp/HarnessGradCode · 8 Oct 2026 · zjunlp · 26 stars
- AlphaDiana: A Measurement System for Agents in Verifiable Reasoning TasksPapers · 14 Oct 2026 · Zhanke Zhou, Zongze Li, Weikai Huang, Xuan Li, Chentao Cao, Xiao Feng, Xiangyu L…
- Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure AttributionPapers · 23 Oct 2026 · Zhiyong Cao, Hengjie Zhu, Yongxin Wang, Xuchen Li, Jintao Li, Shuxia Liu, Dunqia…
- When Agents Fail: Model or Harness--Who's to Blame?Papers · 23 Oct 2026 · Shao Zhang, Hangfan Zhang, Yuanyuan Shi, Hao Li, Min-Le Su, Kangcong Li, Jingpin…
- garrytan/g-harness-evalsCode · 5 Nov 2026 · garrytan · 155 stars
Latest sources
- garrytan/g-harness-evalsCode · 5 Nov 2026 · garrytan · 155 stars
- When Agents Fail: Model or Harness--Who's to Blame?Papers · 23 Oct 2026 · Shao Zhang, Hangfan Zhang, Yuanyuan Shi, Hao Li, Min-Le Su, Kangcong Li, Jingpin…
- Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure AttributionPapers · 23 Oct 2026 · Zhiyong Cao, Hengjie Zhu, Yongxin Wang, Xuchen Li, Jintao Li, Shuxia Liu, Dunqia…
- AlphaDiana: A Measurement System for Agents in Verifiable Reasoning TasksPapers · 14 Oct 2026 · Zhanke Zhou, Zongze Li, Weikai Huang, Xuan Li, Chentao Cao, Xiao Feng, Xiangyu L…
- zjunlp/HarnessGradCode · 8 Oct 2026 · zjunlp · 26 stars