# A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

arXiv: https://arxiv.org/abs/2509.03871 · HTML: https://mlsanity.com/paper/2509.03871/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 232 of its 365 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 232)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)

## Built on by (most cited first, 25 of 25)

- [Are Your Agents Upward Deceivers?](https://mlsanity.com/paper/2512.04864/) (2025)
- [DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models](https://mlsanity.com/paper/2509.24296/) (2025)
- [What Matters For Safety Alignment?](https://mlsanity.com/paper/2601.03868/) (2026)
- [Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries](https://mlsanity.com/paper/2605.18891/) (2026)
- [Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails](https://mlsanity.com/paper/2510.11570/) (2025)
- [MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.16940/) (2025)
- [SafeRBench: Dissecting the Reasoning Safety of Large Language Models](https://mlsanity.com/paper/2511.15169/) (2025)
- [FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization](https://mlsanity.com/paper/2602.03507/) (2026)
- [Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations](https://mlsanity.com/paper/2511.12001/) (2025)
- [Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient](https://mlsanity.com/paper/2602.02313/) (2026)
- [Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs](https://mlsanity.com/paper/2602.11528/) (2026)
- [From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space](https://mlsanity.com/paper/2604.14142/) (2026)
- [Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs](https://mlsanity.com/paper/2510.07697/) (2025)
- [Pause or Fabricate? Training Language Models for Grounded Reasoning](https://mlsanity.com/paper/2604.19656/) (2026)
- [MM-THEBench: Do Reasoning MLLMs Think Reasonably?](https://mlsanity.com/paper/2601.22735/) (2026)
- [Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection](https://mlsanity.com/paper/2604.07831/) (2026)
- [ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models](https://mlsanity.com/paper/2606.23404/) (2026)
- [EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language Models](https://mlsanity.com/paper/2602.02295/) (2026)
- [Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs](https://mlsanity.com/paper/2604.02230/) (2026)
- [Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework](https://mlsanity.com/paper/2604.04852/) (2026)
- [Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models](https://mlsanity.com/paper/2606.11046/) (2026)
- [Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports](https://mlsanity.com/paper/2607.17122/) (2026)
- [Risky Business: Measuring The Faithfulness-Safety Tension](https://mlsanity.com/paper/2608.03745/) (2026)
- [Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models](https://mlsanity.com/paper/2610.05472/) (2026)
- [Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation](https://mlsanity.com/paper/2610.17607/) (2026)

## Abstract (arXiv)

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermediate reasoning steps, thereby improving both accuracy and interpretability. However, despite these advancements, a comprehensive understanding of how CoT-based reasoning affects the trustworthiness of language models remains underdeveloped. In this paper, we survey recent work on reasoning models and CoT techniques, focusing on five core dimensions of trustworthy reasoning: truthfulness, safety, robustness, fairness, and privacy. For each aspect, we provide a clear and structured overview of recent studies in chronological order, along with detailed analyses of their methodologies, findings, and limitations. Future research directions are also appended at the end for reference and discussion. Overall, while reasoning techniques hold promise for enhancing model trustworthiness through hallucination mitigation, harmful content detection, and robustness improvement, cutting-edge reasoning models themselves often suffer from comparable or even greater vulnerabilities in safety, robustness, and privacy. By synthesizing these insights, we hope this work serves as a valuable and timely resource for the AI safety community to stay informed on the latest progress in reasoning trustworthiness. A full list of related papers can be found at hrefhttps://github.com/ybwang119/Awesome-reasoning-safetyhttps://github.com/ybwang119/Awesome-reasoning-safety.