arXiv:2606. 05625v1 Announce Type: cross Abstract: Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut while the written reasoning still resembles ordinary problem solving.
arXiv:2604. 23488v2 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models.
arXiv:2604. 23488v3 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models.
arXiv:2608.22103v1 Announce Type: new Abstract: As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasing...
arXiv:2608. 02657v1 Announce Type: cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.
arXiv:2609.32964v2 Announce Type: replace Abstract: Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to...
The paper introduces Gradient Fingerprint (GRIFT), a technique that uses a model’s internal gradient computations to detect reward hacking in reinforcement learning with verifiable rewards. GRIFT compresses gradients of a chain-of-thought (CoT) conditioned on a prompt into a compact representation, which is then used to assess whether the CoT reflects reward hacking. Experiments on math, code, and logical reasoning benchmarks show GRIFT outperforms baselines by over 25% and, when integrated into a rejection fine‑tuning pipeline, reduces reward hacking while improving task performance.
arXiv:2606. 26300v1 Announce Type: new Abstract: A classical intuition holds that verifying a solution is easier than producing one.
arXiv:2608.02657v2 Announce Type: replace-cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While man...
arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete p...
arXiv:2607. 04572v2 Announce Type: replace Abstract: Large language model (LLM) tutors may have access to teacher notes, answer keys, rubrics, or retrieved solutions while producing student-facing explanations.
arXiv:2609.39533v1 Announce Type: new Abstract: During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high r...
arXiv:2604. 01476v2 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task.