Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning

First seen · 7/20/2026, 10:10 PMLatest activity · 7/20/2026, 10:10 PM

SAGE is a prior-conditioned planner for latent world models that replaces random action-proposal initialization with structured latent subgoals. A goal-conditioned generator predicts reachable subgoals over multiple durations, which condition candidate action sequences. A frozen world model then evaluates and refines the proposals before execution. On long-horizon tasks with target offset 150, the reported success rate increases from 12.7% to 64.7% on PushT and from 26.7% to 67.3% on OGBench Cube, while maintaining strong short-horizon performance.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/20, 10:10 PMnot independentRepresentative
    SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning