Abstract
Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations unresolved, reducing planning reliability and wasting inference-time computation. We develop an inference-time monitor that exposes and verifies intermediate plans without disrupting the original decoding trajectory. Building on this monitor, we propose SafeInferCom, a formal verifier-guided framework that preserves valid intermediate plans and directs error correction during generation. Experiments across multiple LRLMs and planning domains reveal reasoning-response inconsistency and limited self-correction under one-shot inference. SafeInferCom improves planning success and accelerates error correction relative to one-shot inference. When combined with iterative refinement, it further improves success while reducing token usage compared with refinement alone. We additionally evaluate SafeInferCom in VirtualHome and provide a real-world robotic-arm demonstration.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xu, W., Fan, J., Liu, M., & Kong, F. (2026). SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning. https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning
MLA 9
Xu, Weizhe, et al. "SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning." https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning.
Chicago (author–date)
Xu, Weizhe, Jialiang Fan, Mengyu Liu, and Fanxin Kong. 2026. "SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning." https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning.
Harvard
Xu, W., Fan, J., Liu, M. and Kong, F. (2026) 'SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning', Available at: https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning.
Vancouver
Xu W, Fan J, Liu M, Kong F. SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning. https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning
IEEE
W. Xu, J. Fan, M. Liu, and F. Kong, "SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning," https://omanscience.com/en/articles/safeinfercom-safe-inference-time-compute-via-verifier-guided-mid-generation-intervention-for-robotic-task-planning.