Image de couverture de livre

Frontier LLMs Still Struggle with Simple Reasoning Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Malek, Alan, Ge, Jiawei, Lazic, Nevena, Jin, Chi, György, András, Szepesvári, Csaba
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language 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

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
par: György, András, et autres
Publié: (2025)

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning
par: Lazić, Nevena, et autres
Publié: (2026)

To Believe or Not to Believe Your LLM
par: Yadkori, Yasin Abbasi, et autres
Publié: (2024)

Mitigating LLM Hallucinations via Conformal Abstention
par: Yadkori, Yasin Abbasi, et autres
Publié: (2024)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
par: Sun, Yiyou, et autres
Publié: (2025)

Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs
par: Park, Jungsoo, et autres
Publié: (2025)

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
par: Jiang, Dongwei, et autres
Publié: (2024)

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
par: Huang, Kaixuan, et autres
Publié: (2025)

Learning to Reason at the Frontier of Learnability
par: Foster, Thomas, et autres
Publié: (2025)

Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systems
par: Kaiser, Magdalena, et autres
Publié: (2024)

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
par: Faisal, Faizan
Publié: (2026)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
par: Guo, Shiyuan, et autres
Publié: (2025)

Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
par: Yang, Bangji, et autres
Publié: (2026)

Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
par: Nezhurina, Marianna, et autres
Publié: (2024)

Can LLMs Follow Simple Rules?
par: Mu, Norman, et autres
Publié: (2023)

Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
par: Plaut, Benjamin, et autres
Publié: (2024)

Transformers Struggle to Learn to Search
par: Saparov, Abulhair, et autres
Publié: (2024)

Balancing optimism and pessimism in offline-to-online learning
par: Sentenac, Flore, et autres
Publié: (2025)

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
par: Zhao, Guojiang, et autres
Publié: (2025)

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
par: Misra, Dipendra, et autres
Publié: (2026)

Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions
par: Zhao, Minda, et autres
Publié: (2026)

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
par: Jin, Bowen, et autres
Publié: (2024)

Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
par: Wang, Zhengxiang, et autres
Publié: (2025)

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
par: Fan, Run-Ze, et autres
Publié: (2025)

Simple Policy Gradients for Reasoning with Diffusion Language Models
par: Zhan, Anthony
Publié: (2025)

Active Task Disambiguation with LLMs
par: Kobalczyk, Katarzyna, et autres
Publié: (2025)

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
par: Liu, Zihan, et autres
Publié: (2024)

Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
par: Lee, Jaehyeok, et autres
Publié: (2024)

Whitening Not Recommended for Classification Tasks in LLMs
par: Forooghi, Ali, et autres
Publié: (2024)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
par: Ramesh, Shyam Sundhar, et autres
Publié: (2026)

ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale
par: Frohmann, Markus, et autres
Publié: (2023)

Early Signs of Steganographic Capabilities in Frontier LLMs
par: Zolkowski, Artur, et autres
Publié: (2025)

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
par: Xiong, Zheyang, et autres
Publié: (2024)

Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
par: Lei, Ge, et autres
Publié: (2025)

Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization
par: Kawakami, Wataru, et autres
Publié: (2025)

Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners
par: Peng, Miao, et autres
Publié: (2025)

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
par: Yuan, Yurun, et autres
Publié: (2025)

Prompt Repetition Improves Non-Reasoning LLMs
par: Leviathan, Yaniv, et autres
Publié: (2025)

Reverse Thinking Makes LLMs Stronger Reasoners
par: Chen, Justin Chih-Yao, et autres
Publié: (2024)

Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
par: Kim, Jaemin, et autres
Publié: (2025)