SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
cs.RO, cs.AI, cs.CL, cs.LO
Submitted: 2026-10-08
Updated: 2026-10-08
Comments: Video: https://youtu.be/dbU7WskCNgY
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Language Models as Higher-Order Planning Formalizers
- SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
- ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
- VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
- Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
- Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
- interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies