HarnessOpt-Bench

What is HarnessOpt-Bench?

Evaluates LLMs optimizing a target agent's harness (prompts, tools, control flow) under budgeted, stochastic evaluation. Scoring is normalized gain over seed…

Released

2026-08-06

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.06301

HarnessOpt-Bench paper

• Paper https://arxiv.org/abs/2608.06301

Which sources cite HarnessOpt-Bench?

• HarnessOpt-Bench

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench