# HoosierHelp: Benchmarking LLM Agents for Social Service Navigation

arXiv: https://arxiv.org/abs/2608.09946 · HTML: https://mlsanity.com/paper/2608.09946/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 91 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 22 of 22)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections](https://mlsanity.com/paper/2504.11281/) (2025)
- [CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications](https://mlsanity.com/paper/2410.13387/) (2024)
- [AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering](https://mlsanity.com/paper/2510.05445/) (2025)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions](https://mlsanity.com/paper/2207.00746/) (2022)
- [AutoData: A Multi-Agent System for Open Web Data Collection](https://mlsanity.com/paper/2505.15859/) (2025)
- [CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions](https://mlsanity.com/paper/2506.01859/) (2025)
- [Non-Collaborative User Simulators for Tool Agents](https://mlsanity.com/paper/2509.23124/) (2025)
- [MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference](https://mlsanity.com/paper/2510.07475/) (2025)
- [NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning](https://mlsanity.com/paper/2412.15547/) (2024)
- [EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering](https://mlsanity.com/paper/2604.05149/) (2026)
- [LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection](https://mlsanity.com/paper/2503.01900/) (2025)
- [NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering](https://mlsanity.com/paper/2510.09854/) (2025)
- [Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction](https://mlsanity.com/paper/2602.02455/) (2026)
- [GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health](https://mlsanity.com/paper/2601.18106/) (2026)

## Abstract (arXiv)

Social service navigation requires connecting help-seeking individuals to resources that satisfy their needs and specific constraints. Although LLM agents offer a promising interface for conversational resource navigation, existing benchmarks do not capture the interaction complexity and constraint-grounding demands of this setting. We introduce HoosierHelp, an interactive benchmark grounded in 3,971 Indiana public social service resources. Agents interact with simulated users, issue structured resource-search calls, handle non-ideal interactions, and select the final resources returned by the tool. HoosierHelp enhances the realism of simulated users by varying their need structure, constraint satisfiability, and behavior patterns, including impatience, rambling, unsupported requests, and self-contradiction. Experiments on 240 samples across seven LLMs show that current LLM agents remain substantially unreliable for social service navigation. Performance drops sharply on fallback-required and self-contradictory conversations, highlighting the need for agents that are more robust to complex and non-ideal user interactions.