# LLM-Guided Future Hypotheses for Horizon-Aware Exploration in Multi-Step Robot Manipulation

- Source: arXiv cs.RO
- Published: 2026-10-27T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/tcr5evs0s2ipim92e8t3ecsda
- Original: https://arxiv.org/abs/2605.29864

## Summary

The paper proposes Future-Experience Conditioning (FEC), which uses a latent representation of a short future video as a condition for closed-loop policies, for exploration and policy adaptation in multi-step robot manipulation. Future clips are generated in three stages: an LLM reasoner performs task-ontology reasoning initialized from the current scene state, a robot-free digital twin rolls out the intended object motion, and a mask-free video diffusion model synthesizes a robot-consistent future clip.