CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making

• URL: http://arxiv.org/abs/2609.09692v1
• Date: Wed, 09 Sep 2026 04:15:20 GMT
• Title: CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making
• Abstract summary: Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-bystep reasoning, creating opportunities for sophisticated autonomous robots.<n>Recent research reveals that reasoning models verbalize their actual decision processes only 25-39% of the time, with 44% degrading on complex tasks.<n>This paper presents CT-SAFR, a multi-layered verification framework achieving 94.2% hallucination detection with sub-500ms latency.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models [44.55124556245543]
  We propose a multi-layered framework, AID-SR, that establishes a closed loop by translating simulator-observed physical states into structured feedback for the LLM designer.<n>We evaluate our approach on tendon-driven continuum robots across a benchmark of 14 tasks spanning reaching, grasping, locomotion, and manipulation.<n>We fabricate three designed robots of AID-SR that successfully complete the task in real-world.
  arXiv  Detail & Related papers  (2026-09-08T04:02:59Z)
• Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety [4.5810763763063225]
  Novel Regret-Dominance Mechanism (MS-RGR) to operationalize safe autonomy.<n>MS-RGR detects silent failures to near-zero and detects risk 17.5 times faster than a sensor-only baseline.<n>MS-RGR amplifies rather than substitutes for model-level safety training.
  arXiv  Detail & Related papers  (2026-09-04T20:01:33Z)
• Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework [0.0]
  TRACE (Transparent Reasoning Architecture for Credible Execution) is a decision framework that ensures every autonomous action can be traced back to sensor evidence.<n>TRACE is model-agnostic yet designed to integrate learning-based perception modules while preserving decision-level auditability.<n>We evaluate the framework using three objective metrics: Evidence Traceability (sensor-to-decision linkage), Decision Reconstructability (post-hoc analysis capability), and Temporal Continuity (audit trail completeness)
  arXiv  Detail & Related papers  (2026-09-02T17:44:25Z)
• Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy [0.0]
  Development of advanced AI systems has largely focused on execution rather than verifying the feasibility actions planning models propose.<n>We propose a LLM-driven verification layer between planning and execution to evaluate action permissibility.<n>We achieve near 85% precision across accept/escalate/reject categories of adversarial attacks, with negligible errors between accepting and rejecting tasks, and errors mostly manifesting at the escalate boundary.
  arXiv  Detail & Related papers  (2026-08-10T17:15:55Z)
• Cybersecurity Detection Classification with Reasoning-enabled Language Models [50.72675435043546]
  A major issue in Security Operations Centers (SOCs) is alert fatigue.<n>Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat.<n>We train a chain-of-thought (CoT) reasoning-enabled triage classifier on real, human-labeled Windows endpoint detections.
  arXiv  Detail & Related papers  (2026-07-30T16:22:13Z)
• AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration [175.74514061083195]
  We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms.<n>On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%.
  arXiv  Detail & Related papers  (2026-05-19T15:49:51Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics [55.05920313034645]
  We introduce Robot-R1, a novel framework that leverages reinforcement learning to enhance embodied reasoning specifically for robot control.<n>Inspired by the DeepSeek-R1 learning approach, Robot-R1 samples reasoning-based responses and reinforces those that lead to more accurate predictions.<n>Our experiments show that models trained with Robot-R1 outperform SFT methods on embodied reasoning tasks.
  arXiv  Detail & Related papers  (2025-05-29T16:41:12Z)
• ABNet: Attention BarrierNet for Safe and Scalable Robot Learning [58.4951884593569]
  Barrier-based method is one of the dominant approaches for safe robot learning. We propose Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving.
  arXiv  Detail & Related papers  (2024-06-18T19:37:44Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty [5.47019032771784]
  We introduce COBRA-PPM, a novel causal Bayesian reasoning architecture that combines causal Bayesian networks and probabilistic programming to perform interventional inference for robot manipulation under uncertainty.<n>We demonstrate its capabilities through high-fidelity experiments on an exemplar block stacking task, where it predicts manipulation outcomes with high accuracy (Pred Acc: 88.6%) and performs greedy next-best action selection with a 94.2% task success rate.
  arXiv  Detail & Related papers  (2024-03-21T15:36:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.