# CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding

arXiv: https://arxiv.org/abs/2512.04111 · HTML: https://mlsanity.com/paper/2512.04111/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 55 of its 116 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 55)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy](https://mlsanity.com/paper/2002.04087/) (2020)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents](https://mlsanity.com/paper/2506.00641/) (2025)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2404.00599/) (2024)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- ["It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmers](https://mlsanity.com/paper/2304.02491/) (2023)

## Built on by (most cited first, 12 of 12)

- [Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation](https://mlsanity.com/paper/2606.15127/) (2026)
- [AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters](https://mlsanity.com/paper/2605.22645/) (2026)
- [Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains](https://mlsanity.com/paper/2606.22484/) (2026)
- [AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning](https://mlsanity.com/paper/2608.29988/) (2026)
- [Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits](https://mlsanity.com/paper/2607.02586/) (2026)
- [Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer](https://mlsanity.com/paper/2604.17883/) (2026)
- [Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption](https://mlsanity.com/paper/2605.30089/) (2026)
- [Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems](https://mlsanity.com/paper/2608.14667/) (2026)
- [JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction](https://mlsanity.com/paper/2608.29616/) (2026)
- [Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era](https://mlsanity.com/paper/2609.05527/) (2026)
- [ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding](https://mlsanity.com/paper/2610.08662/) (2026)
- [Workerville: Towards an Organizational Behavior Account of Agent Safety](https://mlsanity.com/paper/2610.11561/) (2026)

## Abstract (arXiv)

LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans nor benchmarks for LLMs, fail to capture this shift, excluding problems that require both human reasoning to guide solutions and AI efficiency for implementation. We introduce CentaurEval, a unified, ecologically valid benchmark for measuring human-in-the-loop value in coding. CentaurEval's core innovation is its "Collaboration-Necessary" problem templates, which are intractable for standalone LLMs or humans, but solvable through effective collaboration. CentaurEval dynamically instantiates tasks from 45 templates, providing a standardized IDE for humans and a reproducible 450-task toolkit for LLMs. We benchmark 45 participants against 5 LLMs under 4 levels of human intervention. Results show that while LLMs or humans alone achieve poor pass rates (0.67% and 18.89%), human-AI collaboration significantly improves to 31.11%. Our analysis reveals an emerging co-reasoning partnership, challenging the traditional human-tool hierarchy by showing that strategic breakthroughs can originate from either humans or AI.