Image de couverture de livre

"I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Time

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jinkun, Cheng, Fengxiang, Han, Sijia, Keselj, Vlado
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging
par: Su, Guinan, et autres
Publié: (2025)

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
par: Sui, Yuan, et autres
Publié: (2025)

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights
par: Parashar, Shubham, et autres
Publié: (2025)

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
par: Minartz, Koen, et autres
Publié: (2023)

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning
par: Zhong, Tianle, et autres
Publié: (2026)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
par: Ye, Wen, et autres
Publié: (2025)

Adversarial Robustness Overestimation and Instability in TRADES
par: Li, Jonathan Weiping, et autres
Publié: (2024)

Toward Adaptive Reasoning in Large Language Models with Thought Rollback
par: Chen, Sijia, et autres
Publié: (2024)

Generalisation of RLHF under Reward Shift and Clipped KL Regularisation
par: Tang, Kenton, et autres
Publié: (2026)

Ensuring Safety in an Uncertain Environment: Constrained MDPs via Stochastic Thresholds
par: Zuo, Qian, et autres
Publié: (2025)

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
par: Laine, Rudolf, et autres
Publié: (2024)

Experience-Guided Adaptation of Inference-Time Reasoning Strategies
par: Stein, Adam, et autres
Publié: (2025)

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
par: Pan, Rui, et autres
Publié: (2025)

Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
par: Liang, Zhenwen, et autres
Publié: (2024)

TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
par: Ye, Wen, et autres
Publié: (2024)

DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks
par: Shu, Aijie, et autres
Publié: (2026)

STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation
par: Brinke, Kiet Bennema ten, et autres
Publié: (2025)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
par: Zhong, Yisheng, et autres
Publié: (2026)

Decocted Experience Improves Test-Time Inference in LLM Agents
par: Shen, Maohao, et autres
Publié: (2026)

From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inference
par: Deng, Xiangbo, et autres
Publié: (2025)

Think Clearly: Improving Reasoning via Redundant Token Pruning
par: Choi, Daewon, et autres
Publié: (2025)

HEARTS: Benchmarking LLM Reasoning on Health Time Series
par: Li, Sirui, et autres
Publié: (2026)

Dynamic Search for Inference-Time Alignment in Diffusion Models
par: Li, Xiner, et autres
Publié: (2025)

AgentKit: Structured LLM Reasoning with Dynamic Graphs
par: Wu, Yue, et autres
Publié: (2024)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
par: Gu, Renjie, et autres
Publié: (2026)

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks
par: Wang, Tianlong, et autres
Publié: (2024)

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
par: Shi, Wei, et autres
Publié: (2026)

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
par: Shan, Lianlei, et autres
Publié: (2026)

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis
par: Ondras, Jan, et autres
Publié: (2025)

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?
par: Rouillard, Amy, et autres
Publié: (2026)

RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
par: Ko, Hanbum, et autres
Publié: (2026)

Do Transformers Have the Ability for Periodicity Generalization?
par: Liu, Huanyu, et autres
Publié: (2026)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
par: Agarwal, Shivam, et autres
Publié: (2025)

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
par: Zhang, Yanzhi, et autres
Publié: (2025)

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
par: Hu, Xing, et autres
Publié: (2024)

Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
par: Halder, Indranil, et autres
Publié: (2025)

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding
par: Li, Huayu, et autres
Publié: (2026)

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation
par: Anh, Le Vu, et autres
Publié: (2025)

Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
par: Yang, Xiao-Wen, et autres
Publié: (2026)

Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
par: Cheng, Mingyue, et autres
Publié: (2025)