Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
ActObs adds observation-token supervision to SFT, yielding higher pass@k for Qwen3 agents after GRPO on Terminal-Bench 2.0 and code editing.
1 stories, newest first · one card per story
ActObs adds observation-token supervision to SFT, yielding higher pass@k for Qwen3 agents after GRPO on Terminal-Bench 2.0 and code editing.
Today 1.6K readers · 2.5K views · 777 reads · all time 189K views