# Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems

arXiv: https://arxiv.org/abs/2603.26718 · HTML: https://mlsanity.com/paper/2603.26718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning](https://mlsanity.com/paper/2502.12054/) (2025)
- [UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models](https://mlsanity.com/paper/2502.00334/) (2025)
- [FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks](https://mlsanity.com/paper/2601.21165/) (2026)
- [APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning](https://mlsanity.com/paper/2505.05758/) (2025)
- [CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning](https://mlsanity.com/paper/2503.13517/) (2025)
- [Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders](https://mlsanity.com/paper/2405.17044/) (2024)
- [Think like a Scientist: Physics-guided LLM Agent for Equation Discovery](https://mlsanity.com/paper/2602.12259/) (2026)
- [AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models](https://mlsanity.com/paper/2511.13029/) (2025)
- [Can Theoretical Physics Research Benefit from Language Agents?](https://mlsanity.com/paper/2506.06214/) (2025)
- [Towards autonomous quantum physics research using LLM agents with access to intelligent tools](https://mlsanity.com/paper/2511.11752/) (2025)

## Built on by (most cited first, 1 of 1)

- [K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook](https://mlsanity.com/paper/2610.00074/) (2026)

## Abstract (arXiv)

We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of reliable ground truth for novel research problems, the complications introduced by tool use, and the replication challenges due to the continuously changing/updating knowledge base. We discuss strategies for constructing contamination-resistant problems, generating scalable families of tasks, and the need for evaluating systems through multi-turn interactions that better reflect real scientific practice. As an early feasibility test, we demonstrate how to construct a dataset of novel research ideas to test the out-of-sample performance of our system. We also discuss the results of interviews with several researchers and engineers working in quantum science. Through those interviews, we examine how scientists expect to interact with AI systems and how these expectations should shape evaluation methods.