--- license: apache-2.0 base_model: - Qwen/Qwen3.5-27B - Qwen/Qwen3.6-27B - Qwen/Qwen3.8-27B language: - en tags: - agent - tool-use - environments - sft - grpo library_name: transformers --- # LegoEnv checkpoints Checkpoints trained on environments built by **LegoEnv** (*LegoEnv: Self-Evolving Agentic Environments via Modular Recombination*, arXiv: [2611.01834](https://arxiv.org/abs/2611.01834)). Code: https://github.com/JazyJiang/LegoEnv ยท Data: https://huggingface.co/datasets/JazySong/LegoEnv | Folder | Base | Training | Corpus | |---|---|---|---| | `qwen3.5-27b-sft/` | Qwen3.5-27B | SFT, 3 epochs (step 489) | round-1 corpus plus the 3k draw, 5,229 trajectories | | `qwen3.6-27b-sft/` | Qwen3.6-27B | SFT, 3 epochs (step 570) | round-2 corpus, 6,110 trajectories | | `qwen3.8-27b-grpo/` | Qwen3.8-27B | GRPO, step 200, binary verifier reward | 1,516 environments | All three are full-parameter checkpoints in `safetensors`, with the base model's tokenizer and chat template. Training recipe: SFT with global batch 32, peak learning rate 1e-5, cosine decay, 64K sequence length, teacher reasoning kept across turns, assistant turns that received a 4xx tool response excluded from the loss; GRPO from the unmodified base with group size 8, temperature 1.0, 2 epochs over 1,516 prompts, reward = the environment's programmatic verifier (no reward model, no judge). These are the checkpoints reported in the paper's Table 1. ## Evaluation Protocol: AutomationBench 1.0.6, `api` toolset, 50 steps, one rollout per task, reasoning of earlier turns replayed; MCP-Mark 127 tasks; BFCL v4 official weighted average. | Checkpoint | AutomationBench | MCP-Mark | BFCL v4 | |---|---|---|---| | Qwen3.5-27B base | 3.2 | 44.9 | 67.6 | | `qwen3.5-27b-sft` | 23.2 | 60.0 | 67.6 | | Qwen3.6-27B base | 16.0 | 42.5 | 63.0 | | `qwen3.6-27b-sft` | 32.0 | 68.5 | 72.4 | | Qwen3.8-27B base | 37.6 | 73.2 | 71.0 | | `qwen3.8-27b-grpo` | 40.3 | 77.6 | 72.0 | Numbers are the paper's Table 1 (AutomationBench: mean of one to four evaluations of 600 tasks; MCP-Mark and BFCL v4: mean of four evaluations). ## Usage Standard `transformers` loading; use the bundled chat template and pass tools in the OpenAI function-calling format. The models expect the reasoning of earlier turns to be kept in the conversation (`reasoning_content` on assistant messages), as during training. ## License The checkpoints inherit the Apache-2.0 license of their Qwen3 base models. Training data and code are licensed separately (see the dataset and code repositories).