# CausGround adds causal reasoning to embodied planning for long-horizon tasks

> Original title: Why do standard embodied planners struggle with long-horizon tasks? Storing experience as loose text or raw trajectories makes it impossi...

- Source: BAAI
- Published: 2026-11-05T13:46:00.000Z
- Bad Influence: https://badinfluence.news/items/ohb2phubqoftjfb0qgeemrsp0
- Original: https://x.com/BAAIBeijing/status/2118339047592743183

## Summary

CausGround represents visual inputs as explicit object attributes and inter-object relations, discarding irrelevant scene detail. It plans with bidirectional causal reasoning, identifying preconditions backward from the goal and anticipating state changes forward before acting, which BAAI says avoids repetitive deadlocks and trial-and-error.

## Post

Why do standard embodied planners struggle with long-horizon tasks? Storing experience as loose text or raw trajectories makes it impossible to isolate true causal dependencies from irrelevant scene clutter (like fridge color)!

CausGround introduces two core innovations:

1️⃣Factorized World-State:
Decomposes visual inputs into explicit object attributes (door: closed) and inter-object relations (holding: bread), discarding superficial scene noise.

2️⃣Bidirectional Causal Reasoning:
•Backward from Goal: Identifies mandatory Preconditions(e.g., to retrieve bread inside a microwave, the doormust be opened first).

•Forward over Effects: Anticipates environmental state changes before acting, eliminating repetitive deadlocks and trial-and-error.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWWiAxVa8AAuYep.jpg&mode=thumb&exp=1794096000&sig=cdbc08a5f4a2406a)