CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. However, recent research reveals that reasoning models verbalize their actual decision processes only 25-39% of the time, with faithfulness degrading 44% on complex tasks. This paper presents CT-SAFR (Chain-of-Thought Safety and Faithfulness for Robotics), a multi-layered verification framework achieving 94.2% hallucination detection (n = 500, 95% CI: 91.8-95.9%) with sub-500ms latency. Through a warehouse robot case study, this work demonstrates 87% reduction in unsafe reasoning outputs (p < 0.001) and provides recommendations for responsible deployment of reasoning-capable autonomous robots.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 10 of its 14 references that are in the map. First posted on arXiv 9 Sep 2026.
Builds on
10 of 14 references.
Closest ancestors · 1
Same direction, newest first
Other references · 9
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2023Mistral 7Bcited by 3,065
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
- 2022Survey of Hallucination in Natural Language Generationcited by 2,056
- 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
- 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
- 2025Reasoning Models Don't Always Say What They Thinkcited by 388
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
- 2026Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models
- 2026Risky Business: Measuring The Faithfulness-Safety Tension
- 2026Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy
- 2025Training Strategies for Efficient Embodied Reasoning
- 2025A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
- 2025VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots
- 2026VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification