Metraipolis › archive › dc_f1876fbbd562

Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making — arXiv:2609.18591

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18591
License (as archived)
CC0-1.0
Archived
2026-10-15T14:09:24.947Z
SHA-256 of the archived text
d87bb4fd95c92cecf937e203550edaf2e99e980c1f6c61db947146cfd5d23b87
Stable URL of this page
https://metraipolis.com/documento/dc_f1876fbbd562

How to cite

Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making — arXiv:2609.18591 — arXiv (en), https://arxiv.org/abs/2609.18591 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1876fbbd562 (Metraipolis archive dc_f1876fbbd562, sha256 d87bb4fd95c92cecf937e203550edaf2e99e980c1f6c61db947146cfd5d23b87)
BibTeX
@misc{dcf1876fbbd562,
  title = {Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making — arXiv:2609.18591},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18591},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1876fbbd562; sha256 d87bb4fd95c92cecf937e203550edaf2e99e980c1f6c61db947146cfd5d23b87},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18591. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In-context learning (ICL) enables large language model (LLM) agents to improve decisions using interaction history, yet it remains unclear whether such improvement reflects refined internal reasoning or mere extrapolation of statistical patterns. To disentangle these mechanisms, we study LLM agents in multi-agent incomplete-information games that require recursive belief reasoning. By constructing a public goods game and manipulating the statistical structure of historical feedback, we evaluate decision quality against a history-independent rational expectations equilibrium (REE) benchmark. Our experiments reveal that when historical statistical patterns are disrupted, the benefits of longer context largely vanish, degrading decision quality to the no-context baseline in a way sharply amplified by stronger strategic interdependence. These results suggest that, in such strategic environments, ICL behavior is more consistent with statistical extrapolation than with strategic reasoning. Our work extends the mechanistic study of ICL to strategic multi-agent settings, introduces REE as a diagnostic tool for distinguishing reasoning from extrapolation, and provides a reusable framework for probing the boundaries of LLM reasoning in recursive belief tasks.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-17 in econ.GN).
Categorie arXiv: Artificial Intelligence (cs.AI) ; General Economics (econ.GN).
Pagina del lavoro: https://arxiv.org/abs/2609.18591 — 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 2026-10-15T13:51:22.027Z dalla pagina https://arxiv.org/catchup/econ.GN/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).