# ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks

arXiv: https://arxiv.org/abs/2604.20273 · HTML: https://mlsanity.com/paper/2604.20273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [How Useful are Educational Questions Generated by Large Language Models?](https://mlsanity.com/paper/2304.06638/) (2023)
- [Actuarial Applications of Natural Language Processing Using Transformers: Case Studies for Using Text Features in an Actuarial Context](https://mlsanity.com/paper/2206.02014/) (2022)
- [Design, Results and Industry Implications of the World's First Insurance Large Language Model Evaluation Benchmark](https://mlsanity.com/paper/2511.07794/) (2025)

## Abstract (arXiv)

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four LLM roles by adapter: one agent drafts items, one constructs distractors, a third independently verifies both stages and drives bounded one-shot repair loops, and a cost-optimized auxiliary agent handles Wikipedia-note summarization and topic labelling. The items, per-model responses and complete leaderboard are published as a browsable web interface at https://actubench.de/en/, allowing readers and practitioners to inspect individual items without a repository checkout. We evaluate 50 language models from eight providers on two complementary benchmarks -- 100 empirically hardest multiple-choice items and 100 open-ended items scored by an LLM judge -- and report three headline findings. First, multi-agent verification is load-bearing: the independent verifier flags a majority of drafted items on first pass, most of which the one-shot repair loop resolves. Second, locally-hosted open-weights inference sits on the cost-performance Pareto front: a Gemma~4 model running on consumer hardware and a Cerebras-hosted 120B open-weights model dominate the near-zero-cost region, with the latter within one item of the top of the leaderboard. Third, MCQ and LLM-as-Judge rankings differ meaningfully: the MCQ scaffold inflates the performance ceiling, and Judge-mode evaluation is needed to discriminate at the frontier.