arXiv (All)
open access
Harness-agnostic detection and immunization of reward hacking in self-evolving language models
Self-evolving language models improve by proposing candidate updates and keeping whatever raises a visible score. When that score is an imperfect proxy for the capability one actually wants, sustained selection widens the gap between the two. This is reward hacking. We introduce HackProbe, a monitor
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents#1128733
- CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents#1108638
- SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents#987681
- RMB: Reward Model Boosting Mitigates Reward Hacking#1117933
- FATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-shots Learning#972881
Record · ID 927932
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive