# GIF: An agentic generation framework for interactive and functional object compositions for robot learning

- Source: PKU EPIC Lab
- Published: 2026-09-05T06:36:20.000Z
- RoboHot: https://robohot.news/en/items/p6v30ee54d745k5fgjtjp3l5b
- Original: https://arxiv.org/abs/2609.05927

## Summary

PKU EPIC Lab proposes GIF, an agentic generation framework for robot learning that reframes the problem as disentangled reconstruction followed by relative pose recovery. CoGen combines 2D and 3D generative models to produce instance-disentangled meshes and coarse initial poses; GPRM refines the relative poses under joint geometric and physical guidance; and a VLM verifier selects the candidate that best matches the structured specification.

## Why it matters

The paper splits interactive and functional object composition generation into disentangled reconstruction and relative pose recovery, and provides a benchmark of eight contact-geometry classes along with collision-rate figures, which can help readers assess this route to simulation data generation.