DyadMem Benchmark

What is DyadMem?

Long-term agents must remember not only what is true about a user, but also how a particular agent should work with that user as their shared history evolves.

Released

2026-10-02

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2610.03020

DyadMem paper

• Paper https://arxiv.org/abs/2610.03020

Which sources cite DyadMem?

• DyadMem

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

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench