AEGIS: A Backup Reflex for Physical AI
Long-horizon robot manipulation tends to fail gradually: one bad step degrades the state, and the policy spirals into a basin from which it cannot recover. The failure is often visible before it happens. We introduce AEGIS (Activation-probe Early-warning, Gated Inference Switching), a selective escalation method that uses a lightweight probe on a weak policy's frozen activations to detect high-risk steps while there is still time to act. When the probe flags a step, control switches to a stronger separate policy, but only for the steps that need it. On LIBERO-Spatial, AEGIS recovers 10.1% of the trajectories the weak policy alone loses, versus 4.6% for budget-matched blind escalation and ...
| Authors | Josef Chen |
|---|---|
| Primary category | cs.AI |
| Published | 4 June 2026 |
| Last updated at source | 4 June 2026 |
Connected in the knowledge graph
- Kaikaku/aegis-rolloutsDataset · cited by
Models and datasets referencing this paper
- Kaikaku/aegis-rolloutsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.