arXiv Machine Learning July 14, 2026 By Chuyifei Zhang

When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR

Read the original on arXiv Machine Learning →

arXiv:2607. 11022v1 Announce Type: new Abstract: The test suites used as RLVR rewards for code have natural false positives: per-task, persistent, asymmetric errors that accept the same wrong programs every time they appear, unlike the symmetric or resampled noise assumed by existing noise-robustness analyses.

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

arXiv AI

Jun 16

Auditing Reward Hackability in Code RL Training Environments

arXiv:2606. 16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct.

By Shreshth Rajan

llms reinforcement-learning

arXiv AI

Aug 3

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.

By Xiaonan Xu, Wenjing Wu

llms agents

arXiv AI

Jul 9

The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents

arXiv:2607. 07436v1 Announce Type: new Abstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures?

By Xing Zhang, Yanwei Cui, Guanghui Wang, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He

llms agents safety

arXiv Machine Learning

Jul 1

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

arXiv:2606. 31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism.

By Mehmet Iscan

benchmarks

arXiv Machine Learning

Aug 11

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

arXiv:2608. 08008v1 Announce Type: new Abstract: Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning.

By Ibne Farabi Shihab, Fariya Afrin

fine-tuning safety

arXiv AI

Jul 15

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

arXiv:2607. 12962v1 Announce Type: cross Abstract: Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature.

By Mehmet Iscan

llms reinforcement-learning

Related stories

Auditing Reward Hackability in Code RL Training Environments

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models