Method Drift›Tool use / function calling
Superseded baseline#6 of 55 most-superseded
GRPO
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question AnsweringTool use / function calling · 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superseded — cited as a baseline and beaten by newer methods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.”
— Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents“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.”
— RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
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.
- Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
Turn-level TRUSTR beats GRPO · Acc Norm [From Qwen3-4B-Thinking, Turn-level training]
80.83 vs 72.46
- Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
Turn-level TRUSTR beats GRPO · Overall Score [From Qwen3-4B-Thinking, Turn-level training]
48.04 vs 38.98
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.