Búsqueda: chain of thought

520 artículos encontrados.

• Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents

  Xuan Qi · 3 de abril de 2026 · Large Language Models

  How much should a language agent think before taking action? Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains poorly understood. We present a systematic study of CoT bud…

• On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning

  Zhaoyi Li, Xiangyu Xi, Zhengyu Chen, Wei Wang, Gangwei Jiang, Ranran Shen, Linqi Song, Ying Wei, Defu Lian · 3 de abril de 2026 · Large Language Models

  Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models. However, how CoT trajectories from different sources influence the generalization performance of models remains an open question. In this paper, we conduct a compar…

• Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency

  Xingshuai Huang, Derek Li, Bahareh Nikpour, Parsa Omidi · 2 de abril de 2026 · Large Language Models

  Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat reasoning chains that suffer from redundancy and suboptimal performance. In this work, we introduce Hierarchical Chain-…

• Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models

  Md. Abu Bakor Siddique, Shahrin Hossain, Sadman Ahmed Siam, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan · 2 de abril de 2026 · Mathematics, Computing, and Information Processing

  Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the combination of diagrammatic understanding, symbolic manipulation and logical inference. In existing literature, researchers have chiefly focused on synchronising …

• Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?

  Max Kaufmann, David Lindner, Roland S. Zimmermann, and Rohin Shah · 1 de abril de 2026 · Software System Performance and Reliability

  Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which a model's CoT helps us oversee the model - the monitorability of the CoT - can be affected by training, for instance by…

• Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models

  Ji Ma, Wei Suo, Peng Wang, Yanning Zhang · 31 de marzo de 2026 · Mind wandering and attention

  Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from severe hallucination problems due to diminished visual attention during the generation process. However, visual attention de…

• Symbolic Analysis of Grover Search Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization

  Min Chen, Jinglei Cheng, Pingzhi Li, Haoran Wang, Tianlong Chen, Junyu Liu · 31 de marzo de 2026 · Quantum Computing Algorithms and Architecture

  Understanding the high-level conceptual structure of quantum algorithms from their low-level circuit representations is a critical task for verification, debugging, and education. While traditional numerical simulators can calculate output probabilities, they do not explicitly surface the underlying…

• Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

  Guangfu Guo, Xiaoqian Lu, Yue Feng, Mingming Sun · 31 de marzo de 2026 · Multimodal Machine Learning Applications

  Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted from the most informative regions to secondary cues-we propose…

• MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

  Han Wang, Yifan Sun, Brian Ko, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu, Wei Shen, Vedant Jolly, Huan Zhang · 31 de marzo de 2026 · Explainable Artificial Intelligence (XAI)

  Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the decision-critical factors driving the model's behavior, leading to the reduced CoT monitorabilit…

• Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

  Richard J. Young · 30 de marzo de 2026 · Large Language Models

  Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visible answer. This study examines 12 open-weight reasoning models on MMLU and GPQA questions paired with misleading hints. Among the 10,506 cases where models actually followed the hint (choosin…

• When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models

  Binesh Sadanandan, Vahid Behzadan · 30 de marzo de 2026 · Large Language Models

  Large Language Models (LLMs) are increasingly deployed in medical settings, yet their sensitivity to prompt formatting remains poorly characterized. We evaluate MedGemma (4B and 27B parameters) on MedMCQA (4,183 questions) and PubMedQA (1,000 questions) across a broad suite of robustness tests. Our …

• Reinforcing Structured Chain-of-Thought for Video Understanding

  Peiyao Wang, Haotian Xu, Noranart Vesdapunt, Rui Hou, Jingyi Zhang, Haibin Ling, Oleksandr Obiednikov, Ning Zhou, Kah Kuen Fu · 30 de marzo de 2026 · Multimodal Machine Learning Applications

  Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing R…

• Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

  Yunheng Li, Hangyi Kuang, Hengrui Zhang, Jiangxia Cao, Zhaojie Liu, Qibin Hou, Ming-Ming Cheng · 25 de marzo de 2026 · Multimodal Machine Learning Applications

  Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coar…

• Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?

  Richard J. Young · 25 de marzo de 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that actually influence their outputs), a property that prior evalua…

• Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning

  Anshul Solanki, Sanchit Latawa, Koushik Chakraborty, Navneet Kamboj · 25 de marzo de 2026 · Cloud Computing and Resource Management

  Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of data in enterprises. Although Large Language Models (LLMs) like Gemini 2.5 and other LLMs have demonstrated impressive zero-shot capabilities, their high inference costs limit deployment at scale. This …

• DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

  Zhide Zhong, Junfeng Li, Junjie He, Haodong Yan, Xin Gong, Guanyi Zhao, Yingjie Cai, Jiantao Gao, Xu Yan, Bingbing Liu, Yingcong Chen, Liuqing Yang, Haoang Li · 24 de marzo de 2026 · Multimodal Machine Learning Applications

  Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical planning, as well as precise manipulations demanding fine-grained s…

• PA3: Policy-Aware Agent Alignment through Chain-of-Thought

  Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya · 24 de marzo de 2026 · AI in Service Interactions

  Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute…

• Long Chain-of-Thought Reasoning Across Languages

  Josh Barua, Seun Eisape, Kayo Yin, Alane Suhr · 24 de marzo de 2026 · Semantic Web and Ontologies

  While large reasoning models have shown remarkable ability to generate long chains-of-thought (CoTs) in English, we still lack understanding of how these long-form reasoning abilities transfer to the vast majority of the world's languages. In this work, we systematically investigate four key stages …

• Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts

  Xu Liu, Yongheng Zhang, Qiguang Chen, Yao Li, Sheng Wang, Libo Qin · 24 de marzo de 2026 · Multimodal Machine Learning Applications

  Recently, Interleaved-modal Chain-of-Thought (ICoT) reasoning has achieved remarkable success by leveraging both multimodal inputs and outputs, attracting increasing attention. While achieving promising performance, current ICoT methods still suffer from two major limitations: (1) Static Visual Thou…

• Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation

  Richard J. Young · 23 de marzo de 2026 · Embodied and Extended Cognition

  Recent work on chain-of-thought (CoT) faithfulness reports single aggregate numbers (e.g., DeepSeek-R1 acknowledges hints 39% of the time), implying that faithfulness is an objective, measurable property of a model. This paper demonstrates that it is not. Three classifiers (a regex-only detector, a …

• Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

  Xinghao Zhao · 20 de marzo de 2026 · Logic, Reasoning, and Knowledge

  Chain-of-thought (CoT) reasoning improves LLM accuracy, yet detecting failures cheaply remains elusive. We study whether the shape of uncertainty dynamics across reasoning steps--captured by sampling a few answer completions per step--predicts correctness. We introduce entropy-trajectory monotonic…

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

  Yibin Wen, Qingmei Li, Zi Ye, Jiarui Zhang, Zurong Mai, Jing Wu, Shuohong Lou, Yuhang Chen, Henglian Huang, Xiaoya Fan, Yang Zhang, Defeng Gu, Lingyuan Zhao, Yutong Lu, Haohuan Fu, Jianxi Huang, Juepeng Zheng · 20 de marzo de 2026 · Multimodal Machine Learning Applications

  Recent advancements in Vision-Language Models (VLMs) have significantly impacted various industries. In agriculture, these multimodal capabilities hold great promise for applications such as precision farming, crop monitoring, pest detection, and environmental sustainability. However, while several …

• Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought

  Zichen Xie, Wenxi Wang · 20 de marzo de 2026 · Logic, programming, and type systems

  As Large Language Models (LLMs) increasingly assist secure software development, their ability to meet the rigorous demands of Rust program verification remains unclear. Existing evaluations treat Rust verification as a black box, assessing models only by binary pass or fail outcomes for proof hints…

• Balanced Thinking: Improving Chain of Thought Training in Vision Language Models

  Shaked Perek, Ben Wiesel, Avihu Dekel, Nimrod Shabtay, Eli Schwartz · 20 de marzo de 2026 · Multimodal Machine Learning Applications

  Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning data are inherently token-imbalanced. Long <think> traces ove…

• Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain

  Corentin Royer, Debarun Bhattacharjya, Gaetano Rossiello, Andrea Giovannini, Mennatallah El-Assady · 19 de marzo de 2026 · Large Language Models

  Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling fine-grained supervision and improved reliability. Existing m…