cs.AINov 11, 2026

Read and Ignore: What Self-Directed LLM Agents Do in Public Service Scenarios

Authors: Diana Kozachek, Kinjalk Srivastava

Organizations: University of St.Gallen, Switzerland

Abstract

Underspecified instructions leave LLM agents to decide what to do. In public services, staff write these instructions, but the agent's decisions affect residents, patients, and students. We build four expert-validated public-service scenarios with records and decision levers that can be checked in the files, collect 2,4002{,}400 trajectories from ten LLMs under four prompt conditions, and compare them with 1,0001{,}000 runs in a context-free sandbox. Agents read the records in 96.9%96.9\% of open-ended runs and produce an artifact or a self-chosen task in 18.7%18.7\%; with an explicit task, 86.0%86.0\% produce. Domain context does not change how many runs produce (18.7%18.7\% vs.\ 16.0%16.0\%), and the production ranking of the models largely carries over (Spearman 0.790.79), while the ranking by whether a model reads the records does not (0.190.19). Context cuts boundary-probing turns per run by 60%60\%, and some artifacts contradict the records. We contribute a test that a public-service institution can run on its own records before procurement; its rule-based taxonomy needs no labeled data, and scenarios, code, and trajectories are released.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. NEIGHBOR: Aligning Service Behaviour and Evidence Use in an LLM Agent for Community Resident Services

    Nov 1, 2026Zongyou Yang, Yinghan Hou, Xiaokun YangLLM Agent TrainingTool-Augmented Language Model Agents

  2. Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents

    Jul 13, 2026Chenglin Yu, Li Yin, Ying Yu +4Instruction FollowingRuntime Enforcement for AI Agents