Search: chain of thought

524 papers found.

• CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving

  Zhaohui Wang, Tengbo Yu, Hao Tang · 1 December 2025 · Multimodal Machine Learning Applications

  Vision-Language-Action (VLA) models have recently attracted growing attention in end-to-end autonomous driving for their strong reasoning capabilities and rich world knowledge. However, existing VLAs often suffer from limited numerical reasoning ability and overly simplified input-output mappings, w…

• DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA

  Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha, Rajiv Ramnath · 1 December 2025 · Multimodal Machine Learning Applications

  Document visual question answering (DocVQA) requires models to jointly reason over textual content and spatial layout, yet current systems exhibit a sharp accuracy--efficiency trade-off: large teacher models achieve strong grounding but are too expensive for deployment, while compact students suffer…

• Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information

  Lukas Struppek, Dominik Hintersdorf, Hannah Struppek, Daniel Neider, Kristian Kersting · 1 December 2025 · Large Language Models

  Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference latency. Existing efficiency approaches typically focus on model-centric interventions, such as reinforcement learning or s…

• AgriCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture

  Yibin Wen, Qingmei Li, Zi Ye, Jiarui Zhang, Jing Wu, Zurong Mai, Shuohong Lou, Yuhang Chen, Henglian Huang, Xiaoya Fan, Yang Zhang, Lingyuan Zhao, Haohuan Fu, Huang Jianxi, Juepeng Zheng · 1 December 2025 · Multimodal Machine Learning Applications

  Recent advancements in Vision-Language Models (VLMs) have significantly transformed various industries. In agriculture, these dual-modal capabilities offer promising applications such as precision farming, crop monitoring, pest detection, and environmental sustainability. While several Visual Questi…

• Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework

  Nitya Tiwari, Parv Maheshwari, Vidisha Agarwal · 27 November 2025 · Multimodal Machine Learning Applications

  While recent work has extended CoT to multimodal settings, achieving state-of-the-art results on science question answering benchmarks like ScienceQA, the generalizability of these approaches across diverse domains remains underexplored. This work presents a comprehensive analysis of Multimodal Chai…

• Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning

  Zijun Chen, Wenbo Hu, Richang Hong · 26 November 2025 · Explainable Artificial Intelligence (XAI)

  Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However, its reliability is often undermined by the accumulation of errors in intermediate steps. This paper introduces an novel…

• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

  Benjamin Arnav, Pablo Bernabeu-P\'erez, Nathan Helm-Burger, Tim Kostolansky, Hannes Whittingham, Mary Phuong · 26 November 2025 · Explainable Artificial Intelligence (XAI)

  As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model continuously oversees the intermediate reasoning steps of a mo…

• Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage Assessment

  Ehsan Karimi, Nhut Le, Maryam Rahnemoonfar · 26 November 2025 · Multimodal Machine Learning Applications

  Timely and accurate assessment of damages following natural disasters is essential for effective emergency response and recovery. Recent AI-based frameworks have been developed to analyze large volumes of aerial imagery collected by Unmanned Aerial Vehicles, providing actionable insights rapidly. Ho…

• VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis

  Chujie Wang, Zhiyuan Luo, Ruiqi Liu, Can Ran, Shenghua Fan, Xi Chen, Chu He · 26 November 2025 · Multimodal Machine Learning Applications

  The current remote sensing image analysis task is increasingly evolving from traditional object recognition to complex intelligence reasoning, which places higher requirements on the model's reasoning ability and the flexibility of tool invocation. To this end, we propose a new multimodal agent fram…

• DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs

  Zhen Guo, Shanghao Shi, Shamim Yazdani, Ning Zhang, Reza Tourani · 25 November 2025 · Semantic Web and Ontologies

  With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored security vulnerabilities. We present DarkMind, a novel laten…

• VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

  Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang, Xiangyu Yue, Chenyu You · 25 November 2025 · Multimodal Machine Learning Applications

  Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially …

• Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization

  Zijian Wang, Yanxiang Ma, Chang Xu · 25 November 2025 · Large Language Models

  Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a lack of specialized training, recent studies reveal their laten…

• PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation

  Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen, Peiwen Sun, Rongjie Huang, Xiangang Li, Jieping Ye, Wei Xue · 25 November 2025 · Generative Adversarial Networks and Image Synthesis

  Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and …

• L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention

  Yuliang Zhan, Xinyu Tang, Han Wan, Jian Li, Ji-Rong Wen, Hao Sun · 25 November 2025 · Multimodal Machine Learning Applications

  Recently, Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs), but Vision-Language Models (VLMs) still struggle with multi-step reasoning tasks due to limited multimodal reasoning data. To bridge this gap, researchers have explored methods to …

• FireScope: Wildfire Risk Prediction with a Chain-of-Thought Oracle

  Mario Markov (INSAIT, Sofia University), Stefan Maria Ailuro (INSAIT, Sofia University), Luc Van Gool (INSAIT, Sofia University), Konrad Schindler (ETH Zurich), Danda Pani Paudel (INSAIT, Sofia University, ETH Zurich) · 24 November 2025 · Data Visualization and Analytics

  Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer continuous risk maps. Existing methods lack the causal reasoning and multimodal understanding required for reliable generalization. We introduce $\text…

• Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models

  Wenhan Yu, Xinbo Lin, Lanxin Ni, Jinhua Cheng, Lei Sha · 21 November 2025 · Artificial Intelligence in Law

  Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existing legal benchmarks often conflate factual recall with genuine inference, fragment the reasoning process, and overlook t…

• Output Supervision Can Obfuscate the Chain of Thought

  Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner · 18 November 2025 · Mind wandering and attention

  OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can …

• CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training

  Jiahe Qian, Yuhao Shen, Zhangtianyi Chen, Juexiao Zhou, Peisong Wang · 18 November 2025 · Multimodal Machine Learning Applications

  Medical visual question answering could support clinical decision making, yet current systems often fail under domain shift and produce answers that are weakly grounded in image evidence. This reliability gap arises when models attend to spurious regions and when retraining or additional labels are …

• Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations

  Eunkyu Park, Wesley Hanwen Deng, Vasudha Varadarajan, Mingxi Yan, Gunhee Kim, Maarten Sap, Motahhare Eslami · 18 November 2025 · Explainable Artificial Intelligence (XAI)

  Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically pert…

• Geospatial Chain of Thought Reasoning for Enhanced Visual Question Answering on Satellite Imagery

  Shambhavi Shanker, Manikandan Padmanaban, Jagabondhu Hazra · 17 November 2025 · Multimodal Machine Learning Applications

  Geospatial chain of thought (CoT) reasoning is essential for advancing Visual Question Answering (VQA) on satellite imagery, particularly in climate related applications such as disaster monitoring, infrastructure risk assessment, urban resilience planning, and policy support. Existing VQA models en…

• Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM

  Neo Wang, Sonit Singh · 14 November 2025 · Large Language Models

  The course forums are increasingly significant and play vital role in facilitating student discussions and answering their questions related to the course. It provides a platform for students to post their questions related to the content and admin issues related to the course. However, there are se…

• SCoTT: Strategic Chain-of-Thought Tasking for Wireless-Aware Robot Navigation in Digital Twins

  Aladin Djuhera, Amin Seffo, Vlad C. Andrei, Holger Boche, Walid Saad · 12 November 2025 · Robotic Path Planning Algorithms

  Path planning under wireless performance constraints is a complex challenge in robot navigation. However, naively incorporating such constraints into classical planning algorithms often incurs prohibitive search costs. In this paper, we propose SCoTT, a wireless-aware path planning framework that le…

• SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought

  Shourya Batra, Pierce Tillman, Samarth Gaggar, Shashank Kesineni, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary · 12 November 2025 · Adversarial Robustness in Machine Learning

  As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak private information through their internal reasoning processes,…

• PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation

  Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Qiang Yang · 11 November 2025 · Scientific Computing and Data Management

  Compressing Large Language Models (LLMs) into task-specific Small Language Models (SLMs) encounters two significant challenges: safeguarding domain-specific knowledge privacy and managing limited resources. To tackle these challenges, we propose PPC-GPT, a novel unified framework that systematically…

• Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study

  Yongyu Mu, Jiali Zeng, Bei Li, Xinyan Guan, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu · 11 November 2025 · Reinforcement Learning in Robotics

  Despite recent progress in training long-chain-of-thought reasoning models via scaling reinforcement learning (RL), its underlying training dynamics remain poorly understood, and several counterintuitive behaviors persist. This work focuses on three key aspects: (1) We systematically analyze the rol…