Tool use / function calling
xLAM
xLAM: A Family of Large Action Models to Empower AI Agent Systems
Superseded baseline#10 of 55 most-superseded · first seen Sep 5, 2024
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating xLAM. Values are copied from the source paper's tables — verify against the cited paper.
Llama-3.3-DiaFORGE-70B beats xLAM
0.79 vs 0.51
Acc · [Llama-3.3-70B family]
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less RiskyASA beats xLAM
41.94 vs 38.98
Overall First Call Accuracy · [NESTFUL evaluation]
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.