Tool use / function calling
GRPO
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
Superseded baseline#6 of 55 most-superseded · first seen Mar 14, 2025
Superseded — cited as a baseline and beaten by newer methods
2 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites GRPO as a baseline.
GRPO fine-tunes via weight-space RL but requires thousands of rollouts.
“However, their learning signal fundamentally depends on within-group variability: if the rewards within a sampled group have near-zero or even completely zero standard deviation, the group-normalized advantage becomes degenerate and policy updates vanish.”
Beaten on benchmarks
Head-to-head results where a newer method reports beating GRPO. Values are copied from the source paper's tables — verify against the cited paper.
Turn-level TRUSTR beats GRPO
56.35 vs 39.37
Overall Score · [From Qwen3-4B-Thinking, Turn-level training]
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.