EYT-Bench

What is EYT-Bench?

EYT-Bench evaluates multi-turn dialogue capabilities of LLMs using a decoupled three-party setup with user simulation, target modeling, and judging.

Released

2026-07-11

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.10428

EYT-Bench paper

• Paper https://arxiv.org/abs/2607.10428

Which sources cite EYT-Bench?

• EYT-Bench

Related General AI, Language & Knowledge, cs.CL 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