Chi, H., Feng, Z., Lyu, Y., Zheng, C., Luo, L., Ong, Y. S., ... & Yin, H. InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning. In ICML 2025 Workshop on Programmatic Representations for Agent Learning.
Abstract:
Long-horizon planning in robotic manipulation tasks requires translating underspecified, symbolic goals into executable control programs satisfying spatial, temporal, and physical constraints. However, language model-based planners often struggle with long-horizon task decomposition, robust constraint satisfaction, and adaptive failure recovery. We introduce InstructFlow, a multi-agent framework that establishes a symbolic, feedback-driven flow of information for code generation in robotic manipulation tasks. InstructFlow employs a InstructFlow Planner to construct and traverse a hierarchical instruction graph that decomposes goals into semantically meaningful subtasks, while a Code Generator generates executable code snippets conditioned on this graph. Crucially, when execution failures occur, a Constraint Generator analyzes feedback and induces symbolic constraints, which are propagated back into the instruction graph to guide targeted code refinement without regenerating from scratch. This dynamic, graph-guided flow enables structured, interpretable, and failure-resilient planning, significantly improving task success rates and robustness across diverse manipulation benchmarks, especially in constraint-sensitive and long-horizon scenarios.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund (CDF)
Grant Reference no. : C233312007
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund (CDF)
Grant Reference no. : C243512014
This research / project is supported by the National Research Foundation, Singapore - AI Singapore Programme
Grant Reference no. : AISG-NMLP-2024-003
This research / project is supported by the National Research Foundation, Singapore and Infocomm Media Development Authority - Trust Tech Funding Initiative
Grant Reference no. : DTC-RGC-05