离散扩散模型利用不对称性解决前瞻规划任务
Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
AI总结：
离散扩散模型通过反向生成机制在无需复杂遍历机制的情况下解决前瞻规划任务，相比自回归模型更高效。
摘要：
尽管自回归（AR）基于变换器的生成语言模型经常用于前瞻任务，但近期研究指出它们在需要多步前瞻的规划任务中的能力可能存在偏差。在本工作中，我们研究了在前瞻任务上训练AR与非自回归（NAR）模型（如离散扩散模型（dLLMs））时出现的不同的涌现机制。通过要求模型提前规划以达到正确结论，我们分析了这两种范式在解决问题时的根本差异。我们发现规划问题中存在关键的不对称性：尽管前向生成在分支路口需要复杂的前瞻，反向生成往往是确定性的。这种不对称性为NAR模型提供了机会。通过训练和推理动态的机理分析，我们证明NAR模型通过利用未来令牌反向解码来解决规划任务，从而避免完全学习复杂的遍历机制。因此，我们报告说AR和NAR模型都能在前瞻任务上达到完美准确率。然而，NAR模型相比AR模型需要指数级更少的训练示例和更浅的架构，而AR模型往往在没有特定课程调整的情况下无法收敛。
英文摘要：
Discrete diffusion models are often said to outperform autoregressive models on planning tasks, but the specific mechanisms enabling this are not yet well understood. To explain why, we abstract the complexity of studying "planning" into graph traversal problems, which offer a minimal setup for evaluating language models' planning and lookahead capabilities. We find that non-autoregressive language models are able to leverage an inherent directional asymmetry in lookahead planning tasks to outperform the training efficiency of their autoregressive counterparts. Through a mechanistic study of the training and inference dynamics of autoregressive and non-autoregressive models, we discover that while forward traversal through junctions in the graph requires complex sequential planning, the reverse path remains deterministic. Consequently, non-autoregressive models naturally develop a fundamentally different solution strategy. Effectively, they learn a reverse-decoding pattern which reduces an $\ell^{th}$-order lookahead problem to a sequence of simple $1^{st}$-order transitions. Latent-space analysis further confirms these divergent strategies by demonstrating the distinct internal representations formed during generation. Ultimately, these findings highlight the advantages of non-autoregressive modeling while clarifying the inherent planning limitations induced by autoregressive architectures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
