用向量空间快速规划，避免逐字生成的高耗时问题
Textual Planning with Explicit Latent Transitions
- 在冻结的语义嵌入空间中预测下一步状态，跳过完整推理过程
- 插值任务准确率接近完美，跨域泛化时性能急剧下降
- 适合需要快速多步推演但不跨领域应用的场景
基于大模型的规划受限于逐标记生成和重复前向传播，导致多步前瞻和基于回溯的搜索在延迟和计算上代价高昂。我们提出EmbedPlan，用轻量级转移模型替代自回归的下一步状态生成，该模型在冻结的语言嵌入空间中运行。EmbedPlan将自然语言的状态与动作描述编码为向量，预测下一状态嵌入，并通过最近邻相似性检索下一状态，实现无需微调编码器的快速规划计算。我们在九个经典规划领域中，使用六种难度递增的评估协议（插值、计划变体、外推、多领域、跨领域、留一法）评估了下一步状态预测。结果表明：插值任务表现近乎完美，但当泛化需迁移至未见问题或未见领域时性能显著下降；计划变体评估显示模型能泛化到其他计划路径，而非仅记忆已有轨迹。总体而言，冻结嵌入支持在观察完领域转移后学习领域内动态，但跨领域迁移仍是瓶颈。
原文摘要 · Abstract (English)
Planning with LLMs is bottlenecked by token-by-token generation and repeated full forward passes, making multi-step lookahead and rollout-based search expensive in latency and compute. We propose EmbedPlan, which replaces autoregressive next-state generation with a lightweight transition model operating in a frozen language embedding space. EmbedPlan encodes natural language state and action descriptions into vectors, predicts the next-state embedding, and retrieves the next state by nearest-neighbor similarity, enabling fast planning computation without fine-tuning the encoder. We evaluate next-state prediction across nine classical planning domains using six evaluation protocols of increasing difficulty: interpolation, plan-variant, extrapolation, multi-domain, cross-domain, and leave-one-out. Results show near-perfect interpolation performance but a sharp degradation when generalization requires transfer to unseen problems or unseen domains; plan-variant evaluation indicates generalization to alternative plans rather than memorizing seen trajectories. Overall, frozen embeddings support within-domain dynamics learning after observing a domain's transitions, while transfer across domain boundaries remains a bottleneck.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。