rl_mixed-struct-step37_terminus-structured

RL-trained Qwen3-8B with structured tool calls on mixed dataset (200 nl2bash + 500 r2egym + 500 swesmith).

37 RL steps with terminus-structured agent. SWEBench-100: 42% pass@3.

Training Details

• Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
• Training method: rloo-n with terminus-structured agent (structured tool calls: bash, view, edit, create, search)
• Framework: BenSkyRL + Harbor
• Context: 32k (24k input + 8k output)
• Learning rate: 1e-5

SWEBench-Verified Results (100 tasks, pass@3)

Model	SWEBench pass@3
Base SFT (terminus-2)	37%
This model (terminus-structured)	See eval results

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")
tokenizer = AutoTokenizer.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")