# Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning Source: [Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning]() Collection index: [llms.txt]() Data updated: 2026-03-18T05:00:04.466Z Authors: Earl J St Sauver Published: 2026-02-20T09:52:13.000Z ## Abstract Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while diffusion models must coordinate all positions simultaneously. We propose plan conditioning, a training-free method that prepends a short (~100-token) natural-language plan from an AR model to the diffusion model's prompt. The plan serves as a frozen scaffold -- globally visible context that every token position can attend to from the first denoising step. On GSM8K, plan conditioning improves LLaDA-8B-Instruct from 75.6% to 87.2% (+11.6 percentage points), matching a same-size AR model (LLaMA 3.1 8B, 87.7%) despite a 6.4pp weaker baseline. On HumanEval, the gain is +12.8pp (37.2% to 50.0%), showing plans generalize to code. The same plans improve LLaMA by only +5.7pp on GSM8K and +1.3pp on HumanEval -- diffusion models benefit 2-10x more, supporting the coordination-problem hypothesis. Across 5 random seeds, plan-conditioned GSM8K accuracy has zero standard deviation, making diffusion inference highly stable. Ablations reveal the model follows plan strategy (wrong-strategy plans cause -16.3pp) but is robust to plan values (perturbed numbers: -1.1pp), and that planner quality has a sharp threshold: smaller Llama-class plans hurt (-1.6 to -6.8pp) while frontier plans provide the full lift. Attention analysis confirms the mechanism: plan tokens receive 1.8x excess attention during early denoising, declining to uniform as completion tokens solidify. Plan conditioning costs ~$0.002 per problem and adds ~2s of latency. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-step Mathematical Reasoning on DART 5](): Multi-step mathematical reasoning; DART-5; Accuracy: 17.2. - [Science Multiple-Choice Question Answering on ARC Challenge](): science multiple-choice question answering; ARC Challenge; Accuracy: 75.2. - [Mathematical Reasoning on AIME 24 (accuracy, delta)](): Mathematical Reasoning; AIME 24; Accuracy: 3.3. ## Original sources and implementation [Original paper]() [PDF]()