Paper Detail

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

Mohammad Beigi, Ming Jin, Lifu Huang

arxiv Score 4.3

Published 2026-06-08 · First seen 2026-06-09

General AI

Abstract

Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that failure appears. We introduce Proxy Reward Internalization and Mechanistic Exploitation (PRIME), a learned capability to assess task correctness, predict proxy acceptance, and reason about exploitable proxy--gold gaps. In coding RL environments with exploitable pytest rewards, we measure PRIME through chain-of-thought monitoring, direct probes, and activation-level concept vectors. We find that PRIME emerges in a staged sequence before sustained reward hacking, and that its current direct-probe score forecasts later hack onset and severity even when the visible hack rate is still low. PRIME also adapts when the evaluator changes, retargeting to whichever proxy--gold gap remains rewarded and persisting when gold reward suppresses overt hacking, and ablating its activation directions reduces hacking. Across checkpoints, in-domain PRIME tracks out-of-domain misalignment. Together these results suggest that exploitable proxy RL amplifies a proxy-internalization capability upstream of visible hacking, making PRIME a candidate early-warning signal for broader alignment risk.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{beigi2026proxy,
  title = {Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization},
  author = {Mohammad Beigi and Ming Jin and Lifu Huang},
  year = {2026},
  abstract = {Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that failure appears. We introduce Proxy Reward Internalization and Mechanistic Exploitation (PRIME), a learned capability to assess task correctness, predict proxy acceptance, and reason about exploitable proxy--gold gaps. In coding RL environments with exploitable pytest rewards, we measure PRIME through chain-of-thought},
  url = {https://arxiv.org/abs/2606.09711},
  keywords = {cs.AI, cs.LG},
  eprint = {2606.09711},
  archiveprefix = {arXiv},
}

Metadata

{}