In-Context Reinforcement Learning for Tool Use in Large Language Models
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime24
Qwen3-8B (ICRL)
#61
Acc: 64.1
mathematical-reasoning-on-aime-2025
Qwen3-8B (ICRL)
#84
Accuracy: 51.7
Rank counts only results with a code link.