Environment Evolution for Terminal Agents
Ranking
Overall
86
Content
95
Popularity
63
Observed public metrics from 1 member.
Merged summary
TL;DR - This paper introduces off-policy environment evolution, which progressively raises task difficulty to provide sustained training signals for terminal agents. Long-horizon RL using these environments improved two Qwen3.6 models on Terminal-Bench 2.1 by 14.4 and 18.0 percentage points.
- Derives three environment-evolution directions from the multi-turn learning objective.
- Uses a loop-engineered multi-agent harness to evolve environments and schedule successive generations during training.
- Rollouts with Hy4 preview, Claude Opus 5, and GPT-5.6 Sol consistently found the evolved environments more difficult.
- Unlike on-policy co-evolution, the method is designed to keep generating useful challenges as the trained model becomes stronger.
Sources (1)
Environment Evolution for Terminal Agents
Public signals
Hugging Face upvotes 22
TL;DR - This paper introduces off-policy environment evolution, which progressively raises task difficulty to provide sustained training signals for terminal agents. Long-horizon RL using these environments improved two Qwen3.6 models on Terminal-Bench 2.1 by 14.4 and 18.0 percentage points.
- Derives three environment-evolution directions from the multi-turn learning objective.
- Uses a loop-engineered multi-agent harness to evolve environments and schedule successive generations during training.
- Rollouts with Hy4 preview, Claude Opus 5, and GPT-5.6 Sol consistently found the evolved environments more difficult.
- Unlike on-policy co-evolution, the method is designed to keep generating useful challenges as the trained model becomes stronger.