AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

ReaForest: Fostering Generative Video Reasoning for Spatial Planning

Kun Ouyang, Yuanxin Liu, Xinhao Li, Linli Yao, Xiangyu Zeng, Haoning Wu, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

ICML 2026 · Large language models › Reasoning and chain of thought · approach: Efficient and adaptive thinking

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ReaForest, a method to foster generative video reasoning for spatial planning in video generation models, motivated by the gap between verbal CoT in LLMs and visual mental simulation in VGMs.

Problem

Video generation models struggle with visual reasoning tasks such as spatial planning, unlike LLMs with strong textual chain-of-thought reasoning.

Approach

Frames video generation as a generative visual reasoning process for spatial planning; the abstract only identifies two gaps (VGMs are pre-trained without reasoning-oriented supervision, as far as the visible text states) and the remainder is unavailable.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reasoning activation fine-tuning on ReaGen-27k (ablation)ReaForest · VRBenchEM: 0.0 -> 88.4Improved
add text-image alignment to the training data (ablation)ReaForest · VRBenchEM: 85.2 -> 88.4Improved
add ReaTTS test-time scaling (ablation)ReaForest · VRBenchEM: 70.2 -> 88.4Improved
add entropy-aware budget reallocation (ablation)ReaForest · VRBenchEM: 82.3 -> 88.4Improved
add temperature scaling in the softmax allocation (ablation)ReaForest · VRBenchEM: 84.1 -> 88.4Improved
add temperature adaptation (ablation)ReaForest · VRBenchEM: 85.3 -> 88.4Improved
add forest entropy modulation of temperature (ablation)ReaForest · VRBenchEM: 86.0 -> 88.4Improved
add reflective rectification (ablation)ReaForest · VRBenchEM: 81.5 -> 88.4Improved
use hierarchical verification instead of random verification (ablation)ReaForest · VRBenchEM: 61.6 -> 88.4Improved
add hard constraints in verification (ablation)ReaForest · VRBenchEM: 83.7 -> 88.4Improved
add soft constraints in verification (ablation)ReaForest · VRBenchEM: 85.1 -> 88.4Improved
add terminal constraints in verification (ablation)ReaForest · VRBenchEM: 85.7 -> 88.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy