Metraipolis › archive › dc_2da9da10aa41

Engineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents — arXiv:2609.36365

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36365
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:32.438Z
SHA-256 of the archived text
f4a805f9f532ef28a4a252f3c545327e303e525a166fd94ffc91c863f48ac82f
Stable URL of this page
https://metraipolis.com/documento/dc_2da9da10aa41

How to cite

Engineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents — arXiv:2609.36365 — arXiv (en), https://arxiv.org/abs/2609.36365 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2da9da10aa41 (Metraipolis archive dc_2da9da10aa41, sha256 f4a805f9f532ef28a4a252f3c545327e303e525a166fd94ffc91c863f48ac82f)
BibTeX
@misc{dc2da9da10aa41,
  title = {Engineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents — arXiv:2609.36365},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36365},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2da9da10aa41; sha256 f4a805f9f532ef28a4a252f3c545327e303e525a166fd94ffc91c863f48ac82f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36365. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Can interaction formats and textual scaffolds help large language model (LLM) agents make better decisions, and do better decisions come with better explanations? We study these questions in auctions and matching, multi-agent environments with explicit rules and known optimal strategies. These settings let us vary how a decision problem is presented while retaining a benchmark for evaluating behavior. Drawing on human-motivated theories of simplicity, we compare interfaces that elicit a complete bid or ranking with sequential interfaces that make safe choices easier to identify. We then hold the interaction format fixed and vary reasoning scaffolds and rule descriptions. Across four model families, the ascending auction interface substantially reduces bid deviations. The matching comparison also shows why sequential responses require different error accounting from complete rankings. Laying out payoff contingencies and explaining why truth-telling is safe also improve choices, whereas prompts to plan through matching rounds or form beliefs about opponents worsen play overall. In auctions, these behavioral gains are not accompanied by corresponding improvements in measured verbal indicators of strategic understanding in the agents' short stated plans. Other prompts change those indicators without improving bids. Our findings suggest that human-motivated theories of simplicity can inform the design of decision environments for artificial agents. They also show why scaffolds should be evaluated through realized choices as well as explanations: improvements in one need not appear in the other.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36365 — 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 2026-10-07T15:54:53.493Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).