Tool use / function calling

When2Tool / ToolReadable

Superseded baseline#55 of 55 most-superseded

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 When2Tool / ToolReadable as a baseline.

readable tool-use evidence mainly predicts whether the model crosses the first boundary from direct-answer generation into a parser-recognizable tool-call format (boundary entry). However, boundary entry is not equivalent to strict execution
ASA: Activation Steering for Tool-Calling Domain Adaptation

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.