DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations

ArXi:2605.24539v1 Announce Type: new Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire task-specific competence by changing its external harness, while leaving the base model's general capabilities intact. Prior work shows that self-generated rollouts can harness search, suggesting that agents may acquire new task competence through practice.