arXiv AI

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.

arXiv Machine Learning

Jul 14

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

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.

By Chuyifei Zhang

arXiv AI

Jun 9

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

arXiv:2606. 08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking.

By Ziqian Zhong, Ivgeni Segal, Ivan Bercovich, Shashwat Saxena, Kexun Zhang, Aditi Raghunathan

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jun 4

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

arXiv:2606. 04145v1 Announce Type: cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality.

By Guilin Zhang, Chuanyi Sun, Shahryar Sarkani, John M. Fossaceca

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 21

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).

By Hwiwon Lee, Jiawei Liu, Dongjun Kim, Wubing Xia, Ziqi Zhang, Chunqiu Steven Xia, Lingming Zhang

llms agents benchmarks safety

arXiv AI

Aug 3

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

arXiv:2607. 28887v1 Announce Type: cross Abstract: Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain.

By Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia, Gopi Krishnan Rajbahadur, Ahmed E. Hassan

llms 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

Jun 24

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.

By Khanak Khandelwal (Indian Institute of Technology Jodhpur)

llms agents safety

arXiv AI

Aug 12

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.

By Bhaskar Gurram

llms agents benchmarks

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

Specification Grounding Drives Test Effectiveness for LLM Code

arXiv:2607. 06636v1 Announce Type: cross Abstract: Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions.

By Amin Haeri, Mahdi Ghelichi

llms benchmarks

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

arXiv Machine Learning

Jul 10

DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks

arXiv:2607. 07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents.

By Wenqi Huang, Charley Lee, Leonard Tng, Serena Ge

llms agents benchmarks

Related stories