PredAct-Bench

What is PredAct-Bench?

PredAct-Bench evaluates dialogue agents paired with imperfect tools using educational datasets, measuring AI-assisted decision-making and trust metrics.

Released

2026-08-03

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/2608.02372

PredAct-Bench paper

• Paper https://arxiv.org/abs/2608.02372

Which sources cite PredAct-Bench?

• PredAct-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