Tool use / function calling
PEToolLLM
PEToolLLM: Towards Personalized Tool Learning in Large Language Models
Superseded baseline#44 of 55 most-superseded · first seen Feb 26, 2025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 PEToolLLM as a baseline.
They assume preferences are explicitly available (e.g., profiles or past API calls), failing to address the more realistic setting where preferences remain latent and must be inferred from interaction history.
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.
- Apr 20, 2026