arXiv AI July 17, 2026 By Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, Heuiseok Lim

Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

Read the original on arXiv AI →

arXiv:2607. 14552v1 Announce Type: cross Abstract: A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization

arXiv:2608. 15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goal misgeneralization.

By Suyash Maniyar, Armaan Sandhu, Abhishek Mishra

llms benchmarks

arXiv AI

Jul 28

Masked Distillation: Internalizing the Chain-of-Thought in Language Models

arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.

By Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati

llms efficiency

arXiv AI

Aug 11

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

arXiv:2608. 07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.

By Zhengze Huang, Luyang Yu, Di Hong, Xinzhe Huang, Wanyu Lin, Zhixuan Chu, Zhan Qin, Tianhang Zheng

benchmarks safety

arXiv AI

Jul 10

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.

By Benedikt J. Wagner

llms

arXiv Machine Learning

Aug 4

Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics

arXiv:2608. 01522v1 Announce Type: new Abstract: Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning traces are usually unavailable, and models often exhibit an apparent ceiling beyond which additional data yields no further improvement.

By Longtian Bao, Jianyou Wang, Yang Zhang, Youze Zheng, Ramamohan Paturi

llms reinforcement-learning fine-tuning

arXiv AI

2d ago

The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI

arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.

By Masaharu Mizumoto, Dat Nguyen, Zhiheng Han, Xingfu Li, Yo Nakawake, Le Minh Nguyen

llms benchmarks

Related stories

Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization

Masked Distillation: Internalizing the Chain-of-Thought in Language Models

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics

The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI