arXiv AI August 18, 2026 By Suyash Maniyar, Armaan Sandhu, Abhishek Mishra

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 17

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

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.

By Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, Heuiseok Lim

llms fine-tuning efficiency benchmarks

arXiv AI

Jul 14

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.

By Ning Liu

llms benchmarks

arXiv AI

Aug 10

Ask-E: An Environment for Calibrated Question Generation

arXiv:2608. 06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.

By Sarah Pratt, Jae Sung Park, Scott Geng, Ali Farhadi

llms benchmarks

arXiv Computation and Language

Sep 16

Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA

arXiv:2609.16660v1 Announce Type: new Abstract: Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathema...

By Kailong Fan, Anqi Pu, Yichen Wu, Wanhua Li, Yicong Li, Hanspeter Pfister, Huafeng Liu, Xiang Li, Quanzheng Li, Ning Guo

llms reinforcement-learning

arXiv AI

Sep 1

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning

arXiv:2605.11467v2 Announce Type: replace-cross Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberativ...

By Swapnil Parekh, Naman Goyal

llms reinforcement-learning benchmarks safety

arXiv AI

Aug 21

Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation

arXiv:2608. 20256v1 Announce Type: new Abstract: Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to over-computation on easy problems and insufficient computation on difficult ones.

By Gijs Kassenaar, Zhao Yang, Vincent Fran\c{c}ois-Lavet

llms reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

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

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Ask-E: An Environment for Calibrated Question Generation

Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning

Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation