Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime-2026
Agentic ESOpt + Trace2Skill (Qwen3.5-4B)
#39
Accuracy: 71.7
Rank counts only results with a code link.