Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
Open paper
Benchmark
Model
Rank
Results
code-generation-on-terminal-bench-2-1
Terminal-RSI-27B
–
Accuracy: 86.52
code-generation-on-terminal-bench-3-0
Terminal-RSI-27B
–
Accuracy: 16.95
code-generation-on-terminal-bench-4-0
Terminal-RSI-27B
–
Accuracy: 19.84
Rank counts only results with a code link.