AI ethics evidence index Search
Source-linked daily record
Evidence record 3982 · automatically gathered

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended objective. Reward hacking has been observed across a wide range of settings, yet methods for reliably measuring it at scale remain lacking. In this work, we introduce a new evaluation paradigm for measuring reward hacking. Whereas prior studies have primarily analyz

Record details

Published: 20 May 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Agents & autonomy · Shared topic: Environment

Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook

arXiv · 19 May 2026

Shared topic: Agents & autonomy · Shared topic: Environment

How Far Will They Go? Red-Teaming Online Influence with Large Language Models

arXiv · 20 May 2026

Shared topic: Agents & autonomy · Shared topic: Environment

CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing

arXiv · 19 May 2026

Shared topic: Agents & autonomy · Shared topic: Environment

Echo: Learning from Experience Data via User-Driven Refinement

arXiv · 21 May 2026

Shared topic: Agents & autonomy · Shared topic: Environment

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay

arXiv · 19 May 2026

Shared topic: Agents & autonomy · Shared topic: Environment

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

arXiv · 21 May 2026

How to cite this record

ethics.ai (20 May 2026), “Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale,” evidence record 3982, https://ethics.ai/record/3982 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.