English
Related papers

Related papers: EvilGenie: A Reward Hacking Benchmark

200 papers

LLMs have become the go-to choice for code generation tasks, with an exponential increase in the training, development, and usage of LLMs specifically for code generation. To evaluate the ability of LLMs on code, both academic and industry…

Software Engineering · Computer Science 2024-03-29 Chunqiu Steven Xia , Yinlin Deng , Lingming Zhang

Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These…

We demonstrate LLM agent specification gaming by instructing models to win against a chess engine. We find reasoning models like OpenAI o3 and DeepSeek R1 will often hack the benchmark by default, while language models like GPT-4o and…

Artificial Intelligence · Computer Science 2025-08-28 Alexander Bondarenko , Denis Volk , Dmitrii Volkov , Jeffrey Ladish

In this report, we present ML-Dev-Bench, a benchmark aimed at testing agentic capabilities on applied Machine Learning development tasks. While existing benchmarks focus on isolated coding tasks or Kaggle-style competitions, ML-Dev-Bench…

Software Engineering · Computer Science 2025-02-20 Harshith Padigela , Chintan Shah , Dinkar Juyal

As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly challenging. Existing approaches rely on rule-based verifiers…

Artificial Intelligence · Computer Science 2026-04-21 Wentao Shi , Yu Wang , Yuyang Zhao , Yuxin Chen , Fuli Feng , Xueyuan Hao , Xi Su , Qi Gu , Hui Su , Xunliang Cai , Xiangnan He

Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the…

Software Engineering · Computer Science 2025-10-21 Xiangyang Li , Xiaopeng Li , Kuicai Dong , Quanhu Zhang , Rongju Ruan , Xinyi Dai , Xiaoshuang Liu , Shengchun Xu , Yasheng Wang , Ruiming Tang

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Rigorous software testing is crucial for developing and maintaining high-quality code, making automated test generation a promising avenue for both improving software quality and boosting the effectiveness of code generation methods.…

Software Engineering · Computer Science 2025-02-10 Niels Mündler , Mark Niklas Müller , Jingxuan He , Martin Vechev

Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS)…

Software Engineering · Computer Science 2025-05-29 Tobias Lindenbauer , Egor Bogomolov , Yaroslav Zharov

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…

Cryptography and Security · Computer Science 2026-05-20 Elle Najt , Colin Toft , Tyler Tracy , Fabien Roger , Joe Benton

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…

Artificial Intelligence · Computer Science 2026-05-01 Ivan Bercovich

We prove that under five minimal axioms -- multi-dimensional quality, finite evaluation, effective optimization, resource finiteness, and combinatorial interaction -- any optimized AI agent will systematically under-invest effort in quality…

Artificial Intelligence · Computer Science 2026-03-31 Jiacheng Wang , Jinbin Huang

Intelligent assistants powered by Large Language Models (LLMs) can generate program and test code with high accuracy, boosting developers' and testers' productivity. However, there is a lack of studies exploring LLMs for testing Web APIs,…

Software Engineering · Computer Science 2024-09-09 André Pereira , Bruno Lima , João Pascoal Faria

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning…

Computation and Language · Computer Science 2026-05-20 Leyao Wang , Yanan He , Peng Chen , Asaf Yehudai , Yixin Liu , Rex Ying , Michal Shmueli-Scheuer , Arman Cohan

Large language models (LLMs) for automatic code generation have achieved breakthroughs in several programming tasks. Their advances in competition-level programming problems have made them an essential pillar of AI-assisted pair…

Cryptography and Security · Computer Science 2023-10-24 Hossein Hajipour , Keno Hassler , Thorsten Holz , Lea Schönherr , Mario Fritz

Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, and end-to-end…

Software Engineering · Computer Science 2025-06-19 Hongda Zhu , Yiwen Zhang , Bing Zhao , Jingzhe Ding , Siyao Liu , Tong Liu , Dandan Wang , Yanan Liu , Zhaojian Li

Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion…

Cryptography and Security · Computer Science 2026-05-22 Danyu Sun , Jinghuai Zhang , Yuan Tian , Zhou Li

Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. However, they often need many iterations of trial-and-error to generate effective reward…

Machine Learning · Computer Science 2024-10-28 Vishnu Sarukkai , Brennan Shacklett , Zander Majercik , Kush Bhatia , Christopher Ré , Kayvon Fatahalian

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline…

Cryptography and Security · Computer Science 2026-04-21 Ivan Bercovich , Ivgeni Segal , Kexun Zhang , Shashwat Saxena , Aditi Raghunathan , Ziqian Zhong

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench…

Cryptography and Security · Computer Science 2025-03-04 Nicholas Carlini , Javier Rando , Edoardo Debenedetti , Milad Nasr , Florian Tramèr
‹ Prev 1 4 5 6 7 8 10 Next ›