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

Nov 1, 2026

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

Residents who contact a community service desk about a repair or a service charge need answers they can act on, with facts that hold for their case and commitments the desk can keep. In tool-augmented LLM agents, such facts come from documents and records, and the conduct of a service answer is usually specified in a system prompt. We present NEIGHBOR, an LLM agent for community resident services that trains this conduct into the model that drives its tools. NEIGHBOR is deployed on a live resident-service platform for a district of an East Asian city of more than ten million people. It adapts Qwen3-235B-A22B with LoRA on 7,824 supervised fine-tuning examples built from public community-service materials around six service-behaviour targets, among them commitment control and human referral, and the adapted model plans document retrieval and read-only text-to-SQL over the resident's own records. In an offline evaluation with seven configurations, an independent domain expert rated all 350 answers to 50 stratified held-out queries. NEIGHBOR scores 7.74/10 against 5.86 for the same agent running the un-tuned model (+1.88; paired Wilcoxon p<10−8p<10^{-8}; higher on 46 of 50 queries) and improves all six rated dimensions. No tool-augmented answer received a red-line flag (standalone models: 8-14% of answers). An LLM judge ranks the seven configurations much as the expert does (Spearman ρ=0.93ρ=0.93). Its rubric counts specifics absent from the reference answer as fabricated, so it scores tool-grounded answers 1-2 points lower, enough to change which configuration ranks first. For resident-facing agents, service behaviour is a practical fine-tuning target that raises expert-rated answer quality with the tools held fixed.
Jun 1, 2026

CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation

Evaluating LLM agents in realistic service scenarios requires complex task dependencies, imperfect user behavior, and an evaluation that accommodates multiple valid solutions. We introduce CRAB-Bench (Constraint-based Realistic Agent Benchmark) and RUSE (Realistic User Simulation Engine) to address this gap. CRAB-Bench generates tasks via a constraint graph over multiple interdependent entities with structured distractors, requiring agents to reason carefully over thousands of misleading candidates where only a tiny fraction of solutions are valid. RUSE replaces cooperative, template-like simulators with realistic users grounded in human behavioral studies, instantiated across diverse personas and four behavioral dimensions. Experiments on four frontier LLM agents show that the best model achieves only 61% pass@1 on CRAB-Bench, and switching to RUSE causes further drops of up to 57%, concentrated in task-solving ability rather than conversational quality. Information Disclosure is the most damaging behavioral dimension, and agents interacting with RUSE are less likely to admit mistakes, instead masking errors through implicit corrections.
Jul 13, 2026

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

Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP constraints into executable pseudo-code and run them with a program-guided (PG) stack machine that pages the active frame while an LLM performs semantic execution. A three-arm SOPBench study across six models separates representation from runtime: compiled text never significantly hurts and gains up to 16.0 points where official prose underperforms. Runtime guidance is capability-gated. Two strong models independently show positive seven-domain PG contrasts (58:19 and 75:31 discordant pairs), whereas weak models are harmed. A full-program cursor ablation (active frame first, complete program retained) recovers much of the strong-model refusal gain; selective visibility adds a smaller improvement. Paired probe and audit measurements track this divide to spontaneous state discipline rather than reconstruction ability. On Bank the three primary arms rise from 70.4 to 86.4 to 92.8, with 100% refusal correctness. Practical guidance: compile first; enable active-frame paging only after a model-level discipline check.