AuthMem-Bench

What is AuthMem-Bench?

AuthMem-Bench evaluates authority collapse in persistent memory for LLM agents. It uses a paired benchmark holding claims and tasks fixed while varying source…

Released

2026-08-03

Evaluates

Agents, General AI, Language & Knowledge, Safety, Self-Evolution

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.01679

AuthMem-Bench paper

• Paper https://arxiv.org/abs/2608.01679

Which sources cite AuthMem-Bench?

• AuthMem-Bench

Related Agents, General AI, Language & Knowledge, Safety, Self-Evolution 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