arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.
arXiv:2601.03468v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generati...
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
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...
The paper addresses reward hacking in production machine learning systems, focusing on realistic scenarios such as tool calls and long contexts. It introduces a dynamic intervention that perturbs model representations to steer outputs, using vectors derived from labeled rollouts, gradient optimization, and anti-reward-hacking model specifications. The authors demonstrate that this approach can significantly reduce reward hacking with minimal impact on model coherence or capability, and that steering vectors from coding environments generalize to other domains.
arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptab...
RH-Detect is a unified benchmark for detecting reward hacking in language models, aggregating 92,761 examples from eleven public datasets into a common schema with six behavior categories. It evaluates six off‑the‑shelf models on 5,021 open‑ended evaluation units, achieving a top AUROC of 0.962 and over 93% accuracy, though performance drops notably on multi‑turn tool‑use datasets. The study also shows that input format changes and single‑token fine‑tuning can influence detector performance, revealing gaps in deployment‑time monitoring.
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.
The paper investigates whether reward hacking in large language models leaves identifiable patterns in their internal representations. By analyzing frontier open‑source LLMs such as Kimi K3, GLM 5.2, and Qwen 3.8 Max, the authors find that simple difference‑of‑means (DoM) vectors consistently capture a range of hacking behaviors across standard benchmarks like DeepSWE and SWE‑bench. These vectors are both generalizable and interpretable, enabling inexpensive online detection that can even predict future hacks before they occur.
As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes how reward hacking is...
arXiv:2602.13551v3 Announce Type: replace Abstract: Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant...
arXiv:2512. 06343v3 Announce Type: replace-cross Abstract: Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF.
arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.