Metraipolis › archive › dc_44a2ee80d8b7
THEATRON: A Benchmark for Evaluating Persona Persistence in Long-Horizon LLM Decision-Making — arXiv:2611.11487
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11487
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:39.915Z
- SHA-256 of the archived text
133ae4187f2f74f2c389bc9f8f03c92ebb38131647ae38111501b22b72bec218- Stable URL of this page
https://metraipolis.com/documento/dc_44a2ee80d8b7
How to cite
THEATRON: A Benchmark for Evaluating Persona Persistence in Long-Horizon LLM Decision-Making — arXiv:2611.11487 — arXiv (en), https://arxiv.org/abs/2611.11487 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44a2ee80d8b7 (Metraipolis archive dc_44a2ee80d8b7, sha256 133ae4187f2f74f2c389bc9f8f03c92ebb38131647ae38111501b22b72bec218)
BibTeX
@misc{dc44a2ee80d8b7,
title = {THEATRON: A Benchmark for Evaluating Persona Persistence in Long-Horizon LLM Decision-Making — arXiv:2611.11487},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11487},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44a2ee80d8b7; sha256 133ae4187f2f74f2c389bc9f8f03c92ebb38131647ae38111501b22b72bec218},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11487. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing evaluations often test persona expression rather than whether persona information persists in extended decision-making. We introduce THEATRON, a controlled benchmark that uses financial replay to evaluate persona persistence in long-horizon sequential decision-making. In these environments, models conditioned on fixed behavioral-finance personas observe shared daily market evidence and trajectory-specific account-state feedback and make sequential decisions over multi-month trajectories. We evaluate Zero-Shot, One-Shot, and Chain-of-Thought persona injection across four LLMs, using cumulative-return and action trajectories to diagnose within-persona stability, cross-persona separability, and action collapse. Persona conditioning produces systematic behavioral shifts beyond a no-persona baseline, and persona-level separation generally exceeds the variation induced by semantically equivalent descriptions. Nevertheless, these shifts do not reliably form coherent persona-specific policies: apparently stable separation can arise from stereotyped action collapse, while diverse policies can exhibit noisy trajectory switching. These findings expose a gap between observable persona-induced behavior and persistent, context-sensitive persona-conditioned decision policies. Code and benchmark data are publicly available at: this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.11487 — 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 2026-11-10T18:37:52.440Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).