Suche: chain of thought

521 Paper gefunden.

• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?

  Alexander von Recum, Leander Girrbach, Zeynep Akata · 10. Februar 2026 · Advanced Graph Neural Networks

  Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But how robust are these reasoning traces to disruptions that occur within them? To address this question, we introduce a c…

• Pretraining with Token-Level Adaptive Latent Chain-of-Thought

  Boyi Zeng, Yiqin Hao, He Li, Shixiang Song, Feichen Song, Zitong Wang, Siyuan Huang, Yi Xu, ZiWei He, Xinbing Wang, Zhouhan Lin · 10. Februar 2026 · Large Language Models

  Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation without expanding parameters, by internalizing latent Chain-of…

• Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought

  Jianfeng Si, Lin Sun, Weihong Lin, Xiangzheng Zhang · 9. Februar 2026 · Adversarial Robustness in Machine Learning

  Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a result, models may over-refuse benign requests or under-const…

• NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking

  Kang Chen, Zhuoka Feng, Sihan Zhao, Kai Xiong, Junjie Nian, Yaoning Wang, Changyi Xiao, Yixin Cao · 6. Februar 2026 · Explainable Artificial Intelligence (XAI)

  Large language models increasingly spend inference compute sampling multiple chain-of-thought traces or searching over merged checkpoints. This shifts the bottleneck from generation to selection, often without supervision on the target distribution. We show entropy-based exploration proxies follow a…

• Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning

  Donald Ye, Max Loffgren, Om Kotadia, Linus Wong, Jonas Rohweder · 6. Februar 2026 · Embodied and Extended Cognition

  Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect how the model actually reaches its answer, or merely post-hoc justifications. We propose Normalized Logit Difference Dec…

• When Chains of Thought Don't Matter: Causal Bypass in Large Language Models

  Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore · 5. Februar 2026 · Large Language Models

  Chain-of-thought (CoT) prompting is widely assumed to expose a model's reasoning process and improve transparency. We attempted to enforce this assumption by penalizing unfaithful reasoning, but found that surface-level compliance does not guarantee causal reliance. Our central finding is negative: …

• When Chains of Thought Don't Matter: Causal Bypass in Large Language Models

  Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore · 5. Februar 2026 · Large Language Models

  Chain-of-thought (CoT) prompting is widely assumed to expose a model's reasoning process and improve transparency. We attempted to enforce this assumption by penalizing unfaithful reasoning, but found that surface-level compliance does not guarantee causal reliance. Our central finding is negative: …

• Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

  Kiran Tomlinson, Tobias Schnabel, Adith Swaminathan, Jennifer Neville · 4. Februar 2026 · Advanced Graph Neural Networks

  Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial latency and compute costs. We address a fundamental theoretical question: how many reasoning tokens are required to solve a problem as input size grows? By…

• Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization

  Runquan Gui, Jie Wang, Zhihai Wang, Chi Ma, Jianye Hao, Feng Wu · 4. Februar 2026 · Multimodal Machine Learning Applications

  While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chains, this reliance on verbose generation results in significant latency and computational overhead. To address these challenges, we propose \textbf{CoSMo…

• No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs

  Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou · 3. Februar 2026 · Large Language Models

  This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs) is shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT; whereas CoT remains critical for tasks requirin…

• Capabilities and Fundamental Limits of Latent Chain-of-Thought

  Jiaxuan Zou, Yaozhong Xiong, Yong Liu · 3. Februar 2026 · Explainable Artificial Intelligence (XAI)

  Latent Chain-of-Thought (Latent CoT) models promise efficient reasoning via continuous representations, yet exhibit puzzling performance inconsistencies: excelling at exploration (ProsQA: 97.0%) but failing at computation (GSM8K: 34.1%). We reveal that this trade-off is governed by decisional certai…

• Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings

  Yifei Shao, Kun Zhou, Ziming Xu, Mohammad Atif Quamar, Shibo Hao, Zhen Wang, Zhiting Hu, Biwei Huang · 3. Februar 2026 · Multimodal Machine Learning Applications

  We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key intermediate states are inherently visual. We introduce modal-mixed …

• S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs

  Yanrui Du, Sendong Zhao, Yibo Gao, Danyang Zhao, Qika Lin, Ming Ma, Jiayun Li, Yi Jiang, Kai He, Qianyi Xu, Bing Qin, Mengling Feng · 3. Februar 2026 · Large Language Models

  Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning processes, motivating a key question: Can LLMs acquire a fast…

• RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding

  Jiahe Wu, Bing Cao, Qilong Wang, Qinghua Hu, Dongdong Li, Pengfei Zhu · 3. Februar 2026 · Multimodal Machine Learning Applications

  Multimodal Large Language Models (MLLM) are primarily pre-trained on the RGB modality, thereby limiting their performance on other modalities, such as infrared, depth, and event data, which are crucial for complex scenarios. To address this, we propose RGBX-R1, a framework to enhance MLLM's percepti…

• Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language Models

  Sercan Karakaş · 3. Februar 2026 · Large Language Models

  This study evaluates whether state-of-the-art large language models capture the binding relations of Turkish reflexive pronouns. We construct a balanced evaluation set of 100 Turkish sentences that systematically pit local against non-local antecedents for the reflexives kendi and kendisi. We compar…

• ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model

  Xiaoshu Chen, Sihang Zhou, Ke Liang, Taichun Zhou, Xinwang Liu · 2. Februar 2026 · Multimodal Machine Learning Applications

  Compressing long chains of thought (CoT) into compact latent tokens is crucial for efficient reasoning with large language models (LLMs). Recent studies employ autoencoders to achieve this by reconstructing textual CoT from latent tokens, thus encoding CoT semantics. However, treating textual CoT as…

• Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks

  Nathaniel Mitrani Hadida, Sassan Bhanji, Cameron Tice, Puria Radmard · 2. Februar 2026 · Explainable Artificial Intelligence (XAI)

  Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their actions. CoT is also a powerful tool for monitoring the behaviours of these agents: when faithful, they offer interpretations of the model's decision making…

• EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models

  Hongxi Yan, Qingjie Liu, Yunhong Wang · 2. Februar 2026 · Explainable Artificial Intelligence (XAI)

  Large Reasoning Models (LRMs) excel at complex reasoning tasks through extended chain-of-thought generation, but their reliance on lengthy intermediate steps incurs substantial computational cost. We find that the entropy of the model's output distribution in early reasoning steps reliably distingui…

• ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

  Fanmeng Wang, Haotian Liu, Guojiang Zhao, Hongteng Xu, Zhifeng Gao · 2. Februar 2026 · Multimodal Machine Learning Applications

  While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent latent reasoning methods attempt to mitigate this by compressing reasoning processes into latent space, but often suff…

• Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection

  Yuan Li, Jun Hu, Bryan Hooi, Bingsheng He, Cheng Chen · 2. Februar 2026 · Advanced Graph Neural Networks

  Graph-based fraud detection on text-attributed graphs (TAGs) requires jointly modeling rich textual semantics and relational dependencies. However, existing LLM-enhanced GNN approaches are constrained by predefined prompting and decoupled training pipelines, limiting reasoning autonomy and weakening…

• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition

  Junda Wu, Yuxin Xiong, Xintong Li, Sheldon Yu, Zhengmian Hu, Tong Yu, Rui Wang, Xiang Chen, Jingbo Shang, Julian McAuley · 30. Januar 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparency and performance in reasoning tasks. However, conventional CoT methods rely on heuristic sampling without structured m…

• Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

  Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li, Tong Yu, Xiang Chen, Ritwik Sinha, Jingbo Shang, Julian McAuley · 30. Januar 2026 · Large Language Models

  Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles o…

• A Formal Comparison Between Chain of Thought and Latent Thought

  Kevin Xu, Issei Sato · 30. Januar 2026 · Scientific Research and Philosophical Inquiry

  Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the continuous latent space, enabling computation beyond discrete linguistic representations. While both approaches exploit itera…

• Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance

  Baopu Qiu, Hao Chen, Yuanrong Wu, Changtong Zan, Chao Wei, Weiru Zhang, Xiaoyi Zeng · 30. Januar 2026 · Information Retrieval and Search Behavior

  Effective relevance modeling is crucial for e-commerce search, as it aligns search results with user intent and enhances customer experience. Recent work has leveraged large language models (LLMs) to address the limitations of traditional relevance models, especially for long-tail and ambiguous quer…

• Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning

  Yiqun Chen, Jinyuan Feng, Wei Yang, Meizhi Zhong, Zhengliang Shi, Rui Li, Xiaochi Wei, Yan Gao, Yi Wu, Yao Hu, Zhiqiang Pu, Jiaxin Mao · 30. Januar 2026 · Reinforcement Learning in Robotics

  The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcement learning (RL)-based solutions tackle this problem by coupling a length penalty with outcome-based rewards. This simpli…