UTILMEM Benchmark

What is UTILMEM?

Evaluates long-term conversational memory systems on evidence utilization through 1,717 instances across five domains, testing reasoning, implicit retrieval…

Released

2026-08-31

Evaluates

General AI, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.30508

UTILMEM paper and code

• Paper https://arxiv.org/abs/2608.30508
• Code https://github.com/peijunallin/UtilMem

Which sources cite UTILMEM?

• UTILMEM

Related General AI, Language & Knowledge, Reasoning benchmarks

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