English
Related papers

Related papers: Towards Safety Reasoning in LLMs: AI-agentic Delib…

200 papers

As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has become a critical safety concern. While \textit{Chain-of-Thought} (CoT) prompting…

Artificial Intelligence · Computer Science 2026-01-06 Sourena Khanzadeh

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora.…

Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially…

Robotics · Computer Science 2025-05-20 William Chen , Suneel Belkhale , Suvir Mirchandani , Oier Mees , Danny Driess , Karl Pertsch , Sergey Levine

Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which…

Artificial Intelligence · Computer Science 2025-03-03 Pedro Gimenes , Zeyu Cao , Jeffrey Wong , Yiren Zhao

When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to…

Computation and Language · Computer Science 2025-10-21 Yiqi Li , Yusheng Liao , Zhe Chen , Yanfeng Wang , Yu Wang

Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify model weights and must instead intervene at inference time. This…

Cryptography and Security · Computer Science 2026-05-13 Zhenhao Xu , Wenhan Chang , Yichuan Chen , Yuxin Fang , Junhao Liu , Tianqing Zhu

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

Computation and Language · Computer Science 2024-03-18 Jiashuo Sun , Yi Luo , Yeyun Gong , Chen Lin , Yelong Shen , Jian Guo , Nan Duan

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Artificial Intelligence · Computer Science 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially…

Machine Learning · Computer Science 2026-05-26 Nesreen K. Ahmed , Nima Nafisi

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…

Computation and Language · Computer Science 2026-03-09 Patrick Ahrend , Tobias Eder , Xiyang Yang , Zhiyi Pan , Georg Groh

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in large language models (LLMs), especially their reasoning…

Artificial Intelligence · Computer Science 2026-05-08 Jiahui Zhou , Dan Li , Boxin Li , Xiao Zhang , Erli Meng , Lin Li , Zhuomin Chen , Jian Lou , See-Kiong Ng

Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with…

Computation and Language · Computer Science 2026-02-04 Xingshan Zeng , Lingzhi Wang , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

Artificial Intelligence · Computer Science 2025-10-24 Wonje Jeung , Sangyeon Yoon , Minsuk Kahng , Albert No

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le

Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a single mindset; instead, we integrate multiple mindsets within…

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models,…

Artificial Intelligence · Computer Science 2026-05-26 Jingchu Gai , Guanning Zeng , Christina Baek , Chen Wu , J. Zico Kolter , Andrej Risteski , Aditi Raghunathan

Users' physical safety is an increasing concern as the market for intelligent systems continues to grow, where unconstrained systems may recommend users dangerous actions that can lead to serious injury. Covertly unsafe text is an area of…

Computation and Language · Computer Science 2023-05-22 Alex Mei , Sharon Levy , William Yang Wang
‹ Prev 1 4 5 6 7 8 10 Next ›