SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long workflows, leading to brittle failures and avoidable tool and API cost. We propose \texttt{SPIN}, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control. \texttt{SPIN} enforces a strict DAG contract through \texttt{\_validate\_plan\_text} and repair prompting, producing executable plans before downstream execution, and then evaluates DAG prefixes incrementally to stop when the current prefix is sufficient to answer the query. On AssetOpsBench, across 261 scenarios, \texttt{SPIN} reduces executed tasks from 1061 to 623 and improves \emph{Accomplished} from 0.638 to 0.706, while reducing tool calls from 11.81 to 6.82 per run. On MCP Bench, the same wrapper improves planning, grounding, and dependency related scores for both GPT OSS1 and Llama 4 Maverick.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Semi-Peaucellier Linkage and Differential Mechanism for Linear Pinching and Self-Adaptive Grasping
This paper presents the SP-Diff parallel gripper system, addressing the limited adaptability of conventional end-effectors in intelligent industrial automation. The proposed design employs an innovative differential link…
Trajectory PlanningGenMRP: A Generative Multi-Route Planning Framework for Efficient and Personalized Real-Time Industrial Navigation
Existing industrial-scale navigation applications contend with massive road networks, typically employing two main categories of approaches for route planning. The first relies on precomputed road costs for optimal routi…
Autonomous Aerial Robot for High-Speed Search and Intercept Applications
In recent years, high-speed navigation and environment interaction in the context of aerial robotics has become a field of interest for several academic and industrial research studies. In particular, Search and Intercep…
Motion PlanningState EstimationVocal Bursts Intensity PredictionInvestigating Robot Control Policy Learning for Autonomous X-ray-guided Spine Procedures
Imitation learning-based robot control policies are enjoying renewed interest in video-based robotics. However, it remains unclear whether this approach applies to X-ray-guided procedures, such as spine instrumentation, …
Structurally guided task decomposition in spatial navigation tasks
How are people able to plan so efficiently despite limited cognitive resources? We aimed to answer this question by extending an existing model of human task decomposition that can explain a wide range of simple planning…