---
title: World-in-World
description: "ICLR 2026 oral closed-loop utility bench: does the world model help the agent succeed? WorldFoundry imports task summaries; it does not run the loop."
---

World-in-World (Johns Hopkins, with PKU, Princeton, MIT, and Harvard; ICLR 2026 Oral) benchmarks generative world models in a **closed loop** that mirrors agent–environment interaction. **Task success beats visual quality.** A unified online planner and a standardized action API cover four environments:

- Active Recognition
- Active Embodied QA
- Image-Goal Navigation (success + SPL)
- Robotic Manipulation

The paper's findings: visual quality alone does not guarantee success (controllability matters more); action-observation post-training beats upgrading the video generator; inference-time compute helps closed-loop performance.

`world_in_world_average` is the mean over available closed-loop metrics.

Paper: [World-in-World](https://arxiv.org/abs/2510.18135). Project: [world-in-world.github.io](https://world-in-world.github.io/). Code: [World-In-World/world-in-world](https://github.com/World-In-World/world-in-world).

WorldFoundry is a **result importer**. Closed-loop environments, planners, workers, and task scorers execute **upstream**. Bundled assets support parsing and coverage checks only.

<BenchmarkPageSections id="world-in-world" locale="en" />

## How to run

```bash
worldfoundry-eval zoo benchmark-run \
  --benchmark-id world-in-world \
  --mode official-validation \
  --official-results-path <official_results.json> \
  --generated-artifact-dir <generated_videos> \
  --output-dir tmp/world-in-world/official-validation \
  --json
```

Optional `--task` / `--exp-id` scope the import. Default: `WORLDFOUNDRY_WORLD_IN_WORLD_RESULTS_PATH`.

In-tree pointers: `worldfoundry/data/benchmarks/tasks/external/world-in-world.yaml`, `worldfoundry/data/benchmarks/assets/world-in-world`, `worldfoundry/evaluation/tasks/execution/runners/world_in_world`.

Outputs include `scorecard.json` (primary `world_in_world_average`).

[← Benchmark Hub](/docs/evaluation/benchmark-hub)