# LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law

arXiv: https://arxiv.org/abs/2609.27814 · HTML: https://mlsanity.com/paper/2609.27814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla](https://mlsanity.com/paper/2205.11081/) (2022)
- [AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation](https://mlsanity.com/paper/2403.02959/) (2024)
- [AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents](https://mlsanity.com/paper/2408.08089/) (2024)
- [L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit](https://mlsanity.com/paper/2509.00761/) (2025)
- [LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning](https://mlsanity.com/paper/2605.28120/) (2026)
- [MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning](https://mlsanity.com/paper/2509.24922/) (2025)

## Abstract (arXiv)

In statutory question answering, every claim must be traceable to evidence, not merely relevant, since unverifiable labour-rights answers carry serious legal consequences. Current systems fall short: single-pass RAG cannot detect insufficient evidence, while multi-agent legal-debate systems treat grounding as a prompting convention, letting agents cite unretrieved evidence. To address this gap, we introduce LabourCrew, a multi-agent RAG framework built around three grounding mechanisms: StatuteGraph, a graph index that explicitly links chapter, section, proviso, and cross-reference structure rather than fixed-length spans; an Evidence Exchange Protocol that confines advocates and an interpreter to an evidence ledger, making citation to unretrieved text impossible, while a fault-tolerant supervisor board runs advocates in parallel so individual failures degrade rather than crash the system; and a Calibrated Trust Gate that replaces categorical accept/reject decisions with a trust score, thresholded via conformal risk control for a distribution-free bound on the false-accept rate. We evaluate on LabourActQA, a 500-item Bangla question set from the Bangladesh Labour Act, 2006, spanning seven reasoning categories and three difficulty tiers. The framework drives the empirical false-accept rate to 0.081, within the target level (α = 0.10), achieves the highest Answer Relevancy among HyDE RAG, Graph-RAG, and Hierarchical RAG (0.862 > 0.839, 0.815, 0.828), and degrades gradually rather than catastrophically as question difficulty increases. These results show that calibrated abstention, not retrieval quality alone, is what makes legal question answering auditable in low-resource statutory domains.