HarnessDev Benchmark

What is HarnessDev?

HarnessDev evaluates LLMs on creating and evolving runnable agent harnesses, shifting evaluation from task outputs to the infrastructure capabilities…

Released

2026-09-01

Evaluates

Agents, Code & Software, General AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.01437

HarnessDev paper

• Paper https://arxiv.org/abs/2609.01437
• Website https://self-developing-agents.github.io/

Which sources cite HarnessDev?

• HarnessDev

Related Agents, Code & Software, General AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• Active-SWE
• ActiveSciBench