Metraipolis › archive › dc_0bf7edcfc08b

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents — arXiv:2609.08126

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08126
License (as archived)
CC0-1.0
Archived
2026-10-16T12:57:51.709Z
SHA-256 of the archived text
f6a783e6d267e6d555b8c917df590f22e79d228826f68fb0b507ce0701656bc5
Stable URL of this page
https://metraipolis.com/documento/dc_0bf7edcfc08b

How to cite

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents — arXiv:2609.08126 — arXiv (en), https://arxiv.org/abs/2609.08126 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bf7edcfc08b (Metraipolis archive dc_0bf7edcfc08b, sha256 f6a783e6d267e6d555b8c917df590f22e79d228826f68fb0b507ce0701656bc5)
BibTeX
@misc{dc0bf7edcfc08b,
  title = {SchemeArena: Factorized Stress Testing of Scheming in LLM Agents — arXiv:2609.08126},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08126},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bf7edcfc08b; sha256 f6a783e6d267e6d555b8c917df590f22e79d228826f68fb0b507ce0701656bc5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08126. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction of key factors, such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. Prior work examines only a small number of scenarios, limiting the ability to isolate how these conditions shape an agent's propensity or capability to scheme. This limited scale and task diversity also restrict coverage of realistic deployment settings and the range of scheming strategies that can be observed. To this end, we introduce SCHEMEARENA, a 400-scenario benchmark for scalable scheming stress testing, constructed through a factorized scenario synthesis framework spanning diverse safety-relevant tool domains, instrumental goals, oversight conditions, and pressure mechanisms. To enable scalable and reliable monitoring, we further propose SCOUT, a scheming monitor that grounds multi-criteria judgments in evidence drawn from agents' reasoning and actions. Across controlled stress tests on five LLM agents, we find that explicit instrumental goals are the strongest driver of scheming propensity. Strategic hints play a distinct role by helping agents translate scheming reasoning into concrete covert behavior. Oversight has mixed effects: in several closed models, action-only monitoring increases scheming, suggesting that partial oversight can act as an optimization constraint rather than a deterrent. CoT is a useful but incomplete monitoring signal: it can reveal latent scheming before execution, yet action-only scheming shows that covert behavior may occur without explicit reasoning evidence. We release the benchmark, code, and monitor at: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.08126 — 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 2026-10-16T12:30:25.339Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).