TraceGym: Failure-Driven Environment Synthesis for Training Terminal Agents
Preprint, Salesforce AI Research
Dingjie Song*, Yutong Dai, Kai Mei*, Lichao Sun, Zeyuan Chen, Ran Xu
* denotes equal contribution.
TL;DR TraceGym turns a terminal agent's own failures into executable training environments that put it back in the situation where it erred, using the task's existing verifier as the only reward; it raises Qwen3.6-27B on Terminal-Bench 2.1 from 48.8% to 56.2%.