Fast Task Planning with Neuro-Symbolic Relaxation

2025-07-21

AI Summary

In real-world task planning, complex inter-entity relationships induce combinatorial explosion for symbolic planners. Existing neuro-symbolic approaches mitigate this via importance-based search space pruning but often overlook critical entities, leading to fruitless exploration. This paper proposes a neuro-symbolic relaxed planning framework: first, a graph neural network predicts entity importance to construct a simplified task; second, a learnable rule relaxation mechanism dynamically reintroduces omitted critical entities and refines the plan during symbolic expansion. By jointly optimizing efficiency and reliability, the framework avoids the risk of generating unsolvable simplified tasks. Evaluated on synthetic and real-world maze navigation benchmarks, our method achieves an average 20.82% improvement in success rate and a 17.65% reduction in planning time, significantly outperforming state-of-the-art neuro-symbolic baselines.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Real-world task planning requires long-horizon reasoning over large sets of entities with complex relationships and attributes, leading to a combinatorial explosion for classical symbolic planners. To prune the search space, recent methods prioritize searching on a simplified task only containing a few "important" entities predicted by a neural network. However, such a simple neuro-symbolic (NeSy) integration risks omitting critical entities and wasting resources on unsolvable simplified tasks. To enable Fast and reliable planning, we introduce a NeSy relaxation strategy (Flax), combining neural importance prediction with symbolic expansion. Specifically, we first learn a graph neural network to predict entity importance to create a simplified task and solve it with a symbolic planner. Then, we solve a rule-relaxed task to obtain a quick rough plan, and reintegrate all referenced entities into the simplified task to recover any overlooked but essential elements. Finally, we apply complementary rules to refine the updated task, keeping it both reliable and compact. Extensive experiments are conducted on both synthetic and real-world maze navigation benchmarks where a robot must traverse through a maze and interact with movable objects. The results show that Flax boosts the average success rate by 20.82% and cuts mean wall-clock planning time by 17.65% compared with the state-of-the-art NeSy baseline. We expect that Flax offers a practical path toward fast, scalable, long-horizon task planning in complex environments.

Problem

• Addresses combinatorial explosion in long-horizon task planning
• Integrates neural importance prediction with symbolic expansion
• Improves success rate and reduces planning time

Innovation

• NeSy relaxation combines neural and symbolic planning
• Graph neural network predicts key entity importance
• Rule-relaxed task refines plan with overlooked entities