A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

arXiv:2610.05166v1 Announce Type: new Abstract: A safe action is not necessarily a viable one. Under a frozen vision-language-action (VLA) policy, an action can be likely and locally admissible yet leave no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the current action, whereas feasibility depends on the futures that remain after it. We derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation exposes a candidate-dependent feasible-future mass with two roles: its support records whether safe completion remains possible under the frozen continuation process, and its magnitude measures how much weighted safe-completion mass is preserved. Exact evaluation is impractical online, so we develop a selective finite-candidate approximation, derive conditions for recovering the best retained viable candidate, and instantiate it as an alarm-triggered, training-free reranker. On Safety-CHORES, VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. The resulting decoder is tied to an exact policy-relative safe-completion target, yet requires neither retraining of the base policy nor online trajectory rollouts.

Abstract:A safe action is not necessarily a viable one. Under a frozen vision-language-action (VLA) policy, an action can be likely and locally admissible yet leave no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the current action, whereas feasibility depends on the futures that remain after it. We derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation exposes a candidate-dependent feasible-future mass with two roles: its support records whether safe completion remains possible under the frozen continuation process, and its magnitude measures how much weighted safe-completion mass is preserved. Exact evaluation is impractical online, so we develop a selective finite-candidate approximation, derive conditions for recovering the best retained viable candidate, and instantiate it as an alarm-triggered, training-free reranker. On Safety-CHORES, VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. The resulting decoder is tied to an exact policy-relative safe-completion target, yet requires neither retraining of the base policy nor online trajectory rollouts.

Artificial Intelligence (cs.AI); Robotics (cs.RO)

arXiv:2610.05166 [cs.AI]

(or arXiv:2610.05166v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.05166 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

Subiecte conexe