Plan Canvas Boosts Long-Chain Reasoning Accuracy
New research introduces Plan Canvas, a fixed reasoning region architecture that resolves length uncertainty in continuous language flows, improving Deep ProsQA accuracy from 73% to 87%.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
The Plan Canvas architecture improves Deep ProsQA benchmark accuracy for continuous language flow models from 73.0% to 87.0%, raising the valid path share from 30.8% to 59.1%.
Continuous language flows, such as diffusion models, generate text by denoising all positions simultaneously. Adding reasoning creates complexity because trace lengths vary per question, forcing the model to decide trace length, token placement, and answer start position at once.
Plan Canvas addresses this by using a fixed-capacity 'plan region' to hold compact traces, with supervised padding filling unused slots. This fixes the answer's starting position and allows separate denoising clocks for the plan and the answer.
Experiments show that with backbone and canvas length held constant, the method outperforms free-trace baselines on ProsQA and Deep ProsQA, with the largest gains on the longest proofs. These results are from an arXiv preprint and have not yet been independently reproduced.