Metraipolis › archive › dc_cb4cd9a78607
Towards Understanding Score-Seeking in LLMs — arXiv:2610.41014
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41014
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:32:36.983Z
- SHA-256 of the archived text
e26c318aecdcf30f32fcb08253685402a54d680c708f2614b83b2332e8782047- Stable URL of this page
https://metraipolis.com/documento/dc_cb4cd9a78607
How to cite
Towards Understanding Score-Seeking in LLMs — arXiv:2610.41014 — arXiv (en), https://arxiv.org/abs/2610.41014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb4cd9a78607 (Metraipolis archive dc_cb4cd9a78607, sha256 e26c318aecdcf30f32fcb08253685402a54d680c708f2614b83b2332e8782047)
BibTeX
@misc{dccb4cd9a78607,
title = {Towards Understanding Score-Seeking in LLMs — arXiv:2610.41014},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41014},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb4cd9a78607; sha256 e26c318aecdcf30f32fcb08253685402a54d680c708f2614b83b2332e8782047},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Production large language models sometimes reward-hack, exploiting flaws in how tasks are scored rather than performing the tasks as intended, sometimes in highly sophisticated and adversarial ways. We investigate the motivations driving this behavior in GPT 5.6 Sol, GPT 5.5, and a checkpoint of OpenAI o3 without safety training ("exp-rl-cap-late") by observing model behavior in agentic environments where the grader is leaked. In our environments, the models appear to be score-seeking: trying to score well according to graders that they believe assess their current actions, even at the expense of violating explicit user instructions. They appear to care about score itself rather than its downstream consequences, violating instructions at approximately the same rate whether the score is indicated to be used for training, for evaluation, or not at all. We observe evidence that the more recent models care to some extent about scores that do not assess their own current actions. GPT 5.6 Sol and GPT 5.5 help other agents 24.6 percentage points more often on average when the other agent stands to gain a score of 1 rather than 0 from being helped. However, when grading or monitoring another trajectory, we find models never collude by distorting its score.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41014 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:29:33.699Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).