Cover Image

Reasoning Fails Where Step Flow Breaks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Xiaoyu, Pan, Yulan, Yuan, Xiaosong, Shen, Zhihong, Su, Minghao, Su, Yuanhao, Zhang, Xiaofeng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry
by: Alvarez, Tyler, et al.
Published: (2026)

On the Step Length Confounding in LLM Reasoning Data Selection
by: Wang, Bing, et al.
Published: (2026)

LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology
by: Su, Haoyang, et al.
Published: (2026)

Where LLM Agents Fail and How They can Learn From Failures
by: Zhu, Kunlun, et al.
Published: (2025)

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
by: Zhang, Xiaofeng, et al.
Published: (2024)

FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets
by: Ravnik, Jan, et al.
Published: (2026)

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
by: Tyagi, Nemika, et al.
Published: (2024)

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning
by: Xin, Yue, et al.
Published: (2025)

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints
by: Xu, Rui, et al.
Published: (2025)

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
by: Liu, Kaiyuan, et al.
Published: (2025)

Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
by: Rakshit, Sushrita, et al.
Published: (2026)

Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
by: Feng, Yiyang, et al.
Published: (2026)

Tools as Continuous Flow for Evolving Agentic Reasoning
by: Huang, Tairan, et al.
Published: (2026)

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
by: Fan, Sinan, et al.
Published: (2025)

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
by: Du, Huifang, et al.
Published: (2024)

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
by: Ehsani, Ramtin, et al.
Published: (2026)

CardioCoT: Hierarchical Reasoning for Multimodal Survival Analysis
by: Rui, Shaohao, et al.
Published: (2025)

Where Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions
by: Floro, Avrile, et al.
Published: (2026)

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning
by: Mao, Ruixiang, et al.
Published: (2026)

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
by: Wang, Jiaxuan, et al.
Published: (2026)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
by: Zhuang, Ziqing, et al.
Published: (2026)

ST-Mamba: Spatial-Temporal Mamba for Traffic Flow Estimation Recovery using Limited Data
by: Yuan, Doncheng, et al.
Published: (2024)

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
by: Wang, Xinyu Jessica, et al.
Published: (2026)

Deployability-Centric Infrastructure-as-Code Generation: Fail, Learn, Refine, and Succeed through LLM-Empowered DevOps Simulation
by: Zhang, Tianyi, et al.
Published: (2025)

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
by: Kirichenko, Polina, et al.
Published: (2025)

Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
by: Yuan, Chenchen, et al.
Published: (2026)

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
by: Shi, Weijie, et al.
Published: (2025)

MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning
by: Su, Crystal
Published: (2025)

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
by: Kwon, Yongchan, et al.
Published: (2025)

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
by: Liang, Jia, et al.
Published: (2026)

Boosting Deductive Reasoning with Step Signals In RLHF
by: Li, Jialian, et al.
Published: (2024)

Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems
by: Su, Hong
Published: (2026)

MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight Verifier
by: Su, Crystal
Published: (2025)

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
by: Zhang, Qingjie, et al.
Published: (2025)

MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
by: Yan, Yuchen, et al.
Published: (2025)

Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering
by: Wen, Wuzhenghong, et al.
Published: (2026)

Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
by: Hu, Yulan, et al.
Published: (2025)

Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning
by: Rui, Shaohao, et al.
Published: (2025)

A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning
by: Su, Hong
Published: (2025)

Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
by: Gupta, Isha, et al.
Published: (2025)