English
Related papers

Related papers: EvilGenie: A Reward Hacking Benchmark

200 papers

The adoption of Vision-Language Models (VLMs) in embodied AI agents, while being effective, brings safety concerns such as jailbreaking. Prior work have explored the possibility of directly jailbreaking the embodied agents through…

Cryptography and Security · Computer Science 2025-11-21 Chunyang Li , Zifeng Kang , Junwei Zhang , Zhuo Ma , Anda Cheng , Xinghua Li , Jianfeng Ma

Reinforcement learning with verifiable rewards has enabled strong post-training gains in domains such as math and coding, though many open-ended settings rely on rubric-based rewards. We study reward hacking in rubric-based RL, where a…

Artificial Intelligence · Computer Science 2026-05-13 Anas Mahmoud , MohammadHossein Rezaei , Zihao Wang , Anisha Gunjal , Bing Liu , Yunzhong He

While developers increasingly adopt tools powered by large language models (LLMs) in day-to-day workflows, these tools still require explicit user invocation. To seamlessly integrate LLM capabilities to a developer's workflow, we introduce…

Human-Computer Interaction · Computer Science 2025-03-20 Sebastian Zhao , Alan Zhu , Hussein Mozannar , David Sontag , Ameet Talwalkar , Valerie Chen

Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them…

Machine Learning · Computer Science 2026-04-15 Zixuan Liu , Xiaolin Sun , Zizhan Zheng

Agents based on Large Language Models (LLMs) have shown promise for performing sophisticated software engineering tasks autonomously. In addition, there has been progress towards developing agents that can perform parts of the research…

Computation and Language · Computer Science 2026-04-23 Nicholas Edwards , Yukyung Lee , Yujun Audrey Mao , Yulu Qin , Sebastian Schuster , Najoung Kim

Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives…

Artificial Intelligence · Computer Science 2026-02-24 Mohammad Beigi , Ming Jin , Junshan Zhang , Jiaxin Zhang , Qifan Wang , Lifu Huang

To evaluate large language models (LLMs) for code, research has used manually created unit test-based benchmarks. However, these tests are often inadequate, missing corner cases and other implementation-specific oddities. This work…

Software Engineering · Computer Science 2025-02-27 Miltiadis Allamanis , Pengcheng Yin

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

Artificial Intelligence · Computer Science 2026-04-06 Yunhao Feng , Yifan Ding , Yingshui Tan , Xingjun Ma , Yige Li , Yutao Wu , Yifeng Gao , Kun Zhai , Yanming Guo

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during…

Machine Learning · Computer Science 2026-02-12 Han Li , Letian Zhu , Bohan Zhang , Rili Feng , Jiaming Wang , Yue Pan , Earl T. Barr , Federica Sarro , Zhaoyang Chu , He Ye

This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 29 standalone…

Cryptography and Security · Computer Science 2026-02-17 Chihao Shen , Connor Dilgren , Purva Chiniya , Luke Griffith , Yu Ding , Yizheng Chen

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code agent evaluation face two major limitations. First, creating…

Software Engineering · Computer Science 2026-03-24 Lingyue Fu , Bolun Zhang , Hao Guan , Yaoming Zhu , Lin Qiu , Weiwen Liu , Xuezhi Cao , Xunliang Cai , Weinan Zhang , Yong Yu

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and…

Software Engineering · Computer Science 2026-04-27 Jia Li , Hongyi Deng , Yiran Zhang , Kechi Zhang , Tianqi Shao , Tiankuo Zhao , Weinan Wang , Zhi Jin , Ge Li , Yang Liu , Yingtao Fang , Yihong Dong

Recent advancements in large language models (LLMs) have led to remarkable performance across a wide range of language understanding and mathematical tasks. As a result, increasing attention has been given to assessing the true reasoning…

Computation and Language · Computer Science 2025-03-14 Jonas Golde , Patrick Haller , Fabio Barth , Alan Akbik

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios…

Cryptography and Security · Computer Science 2026-05-27 Hwiwon Lee , Jiawei Liu , Dongjun Kim , Ziqi Zhang , Chunqiu Steven Xia , Lingming Zhang

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and…

Artificial Intelligence · Computer Science 2024-04-10 Luca Gioacchini , Giuseppe Siracusano , Davide Sanvito , Kiril Gashteovski , David Friede , Roberto Bifulco , Carolin Lawrence

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As…

Machine Learning · Computer Science 2026-01-29 Silvia Sapora , Devon Hjelm , Alexander Toshev , Omar Attia , Bogdan Mazoure

Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove…

Programming Languages · Computer Science 2026-04-21 Lingfei Zeng , Fengdi Che , Xuhan Huang , Fei Ye , Xu Xu , Binhang Yuan , Jie Fu

Deductive verification provides strong correctness guarantees for code by extracting verification conditions (VCs) and writing formal proofs for them. The expertise-intensive task of VC proving is the main bottleneck in this process, and…

Software Engineering · Computer Science 2026-03-24 Huan Zhao , Haoxin Tu , Zhengyao Liu , Martin Rinard , Abhik Roychoudhury

Large Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by…

Computation and Language · Computer Science 2025-08-15 Hongchao Jiang , Yiming Chen , Yushi Cao , Hung-yi Lee , Robby T. Tan

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Artificial Intelligence · Computer Science 2026-01-23 Manish Bhatt