arXiv (All)
open access
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the underlying response quality. This phenomenon is amplified in group-relative policy optimization: an unsupported reward can sh
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
- LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking#19015
- Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR#999743
- NOT ALL CORRECT ANSWERS ARE EQUAL: EXAMINING THE ROLE OF STRATEGY IN REPEATING PATTERN ABSTRACTION#671587
- Is the SEC a Learning Regulator? Lessons from Proxy Access#494508
- Murphy’s Laws of AI Alignment: Why the Gap Always Wins#73213
Record · ID 1132101
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