Metraipolis › archive › dc_137dc25a67ad

A Framework for Context Enrichment and Selective Robustness in LLM Social Agents — arXiv:2611.06914

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06914
License (as archived): CC0-1.0
Archived: 2026-11-05T18:16:22.902Z
SHA-256 of the archived text: ee1b6e1acd7a1a017fd2e2056efe0e63f654ea1fdf2b159af3ae4fb395239603
Stable URL of this page: https://metraipolis.com/documento/dc_137dc25a67ad

How to cite

A Framework for Context Enrichment and Selective Robustness in LLM Social Agents — arXiv:2611.06914 — arXiv (en), https://arxiv.org/abs/2611.06914 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_137dc25a67ad (Metraipolis archive dc_137dc25a67ad, sha256 ee1b6e1acd7a1a017fd2e2056efe0e63f654ea1fdf2b159af3ae4fb395239603)

BibTeX

@misc{dc137dc25a67ad,
  title = {A Framework for Context Enrichment and Selective Robustness in LLM Social Agents — arXiv:2611.06914},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06914},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_137dc25a67ad; sha256 ee1b6e1acd7a1a017fd2e2056efe0e63f654ea1fdf2b159af3ae4fb395239603},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06914. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Researchers use large language models as agents in social simulations, where agents are prompted with observations and background information intended to shape their actions. Yet LLM agents have been shown to substantially change their behavior under meaning-preserving prompt variations, creating a validation problem for social simulation. One plausible hypothesis is that this brittleness reflects a lack of grounding and can be reduced by enriching the context provided to the agents. Whether richer context improves robustness remains unclear, in part because context richness and robustness are rarely defined in ways that support controlled comparisons. We address the first need with controlled context enrichment, a set of prompt substitution rules that systematically enriches distinct types of context: neutral padding, generic social background, descriptive decision grounding, and normative decision grounding. We address the second by introducing selective robustness as a validation criterion: insensitivity to meaning-preserving prompt variation combined with a directional response to decision-relevant changes in the social world. We demonstrate the framework in a Prisoner's Dilemma-like game, showing how it can be used to identify which forms of context enrichment produce more desirable and robust agent behavior. We find that these forms of enrichment produce distinct behavioral patterns that vary between the two models tested.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.06914 — 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 2026-11-05T18:10:09.309Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).