Tool use / function calling

Mem0

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Superseded baseline#41 of 55 most-superseded · first seen Apr 28, 2025

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites Mem0 as a baseline.

Recent benchmarks for tool use evaluate an agent's ability to invoke external APIs in multi-turn settings ... However, they treat tool use as a decision process based solely on the current dialogue state, ignoring prior interactions.
Latent Preference Modeling for Cross-Session Personalized Tool Calling

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.