# Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection arXiv: https://arxiv.org/abs/2610.18881 · HTML: https://mlsanity.com/paper/2610.18881/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. - Builds on 36 of its 49 references that are in the map. - First posted on arXiv 1 Oct 2026. ## Placed in - LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/) ## Builds on (most cited first, 30 of 36) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022) - [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024) - [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025) - [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025) - [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019) - [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020) - [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019) - [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023) - [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023) - [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025) - [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025) - [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018) - [Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.00783/) (2021) - [Training Neural Response Selection for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1906.01543/) (2019) - [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024) - [Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning](https://mlsanity.com/paper/1702.03274/) (2017) - [SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents](https://mlsanity.com/paper/2506.08119/) (2025) - [End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs](https://mlsanity.com/paper/2109.07263/) (2021) - [FlowAgent: Achieving Compliance and Flexibility for Workflow Agents](https://mlsanity.com/paper/2502.14345/) (2025) - [Towards Enforcing Company Policy Adherence in Agentic Workflows](https://mlsanity.com/paper/2507.16459/) (2025) - [Schema-Guided Paradigm for Zero-Shot Dialog](https://mlsanity.com/paper/2106.07056/) (2021) - [Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent](https://mlsanity.com/paper/2502.18228/) (2025) - [Task-Oriented Dialogue with In-Context Learning](https://mlsanity.com/paper/2402.12234/) (2024) - [AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents](https://mlsanity.com/paper/2607.02599/) (2026) - [ASR error management for improving spoken language understanding](https://mlsanity.com/paper/1705.09515/) (2017) - [PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents](https://mlsanity.com/paper/2606.29225/) (2026) - [Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial](https://mlsanity.com/paper/2603.05413/) (2026) - [Toward An Optimal Selection of Dialogue Strategies: A Target-Driven Approach for Intelligent Outbound Robots](https://mlsanity.com/paper/2206.10953/) (2022) ## Abstract (arXiv) Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a conversational flow set by law. In debt collection, it must confirm it is speaking to the debtor before mentioning the debt, identify itself and the creditor, state the amount, and avoid prohibited language. Every creditor turns these rules into its own procedure and revises it. We ask whether a small, self-hosted policy can be trained once and then follow regulated procedures it has never seen. One machine-readable specification per deployment, FlowSpec, generates the policy instruction, gates the tools, supplies the supervision and defines the tests; the agent speaks only approved catalogue sentences. We fine-tune a 9-billion-parameter model on 2,506 conversations from 297 randomized procedures and evaluate a Thai outbound-call agent on four unseen deployment procedures (three debt collection, one non-debt), one from a wholly withheld lineage. Documented checks, fixed by the procedure, rise from 67--71 percents to 93--100 percents, while grounded checks, fixed by the conversation, already pass at 97--100 percents before training; scenario pass rate rises from 15/43 to 40/43. An audit of the shared specification finds 11 defects, 3 of which its own metric did not expose.