Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security
Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security
This research presents a framework for program-level adversarial co-adaptive self-play, where coding agents generate attacks and defenses from tested opponent code and mission feedback without model fine-tuning. The study includes two eight-generation case studies showing that while the framework enables local task recovery in autonomous driving and humanoid locomotion scenarios, it does not establish sustained robustness against evolving opponents.
The paper introduces a framework for program-level adversarial co-adaptive self-play where coding agents generate attacks and defenses without model fine-tuning, demonstrating local task recovery in autonomous driving and humanoid locomotion scenarios but noting that sustained robustness is not established.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.36143v2 Announce Type: replace Abstract: Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not remain effective. We present a framework for program-level adversarial co-adaptive self-play in which coding agents generate attacks and defenses from tested opponent code and mission feedback, without model fine-tuning. Environment-spec
Open source S2
ific interfaces support external programs for autonomous driving and SDK-level defenses for humanoid locomotion. Two eight-generation case studies reveal concrete software responses: a driving defender introduces direct-actuation recovery, while a humanoid defender revises incoming-state validation. These responses provide local task recovery but do not establish sustained robustness. The framework makes such adaptat
Open source S3
ion and limitations observable through executable artifacts and task-level evidence.
Open source S4
Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org